1{2 "seshat_polaris2026": {3 "dataset": "Seshat Global History Databank — Polaris-2026 snapshot",4 "publisher": "Seshat: Global History Databank (University of Oxford / Complexity Science Hub)",5 "release": "Polaris-2026 (repository commit 55ca5fbc2b, 2026-02-25, 'final version')",6 "url": "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Polaris2026.xlsx",7 "landing_page": "https://seshatdatabank.info/data/",8 "license": "MIT (repository LICENSE, Copyright (c) 2025 Seshat Global History Databank); data citation requested",9 "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)",10 "filename": "Polaris2026.xlsx",11 "units": "polity-time rows; variables coded 0/1 (absent/present) or numeric with uncertainty ranges; see sheets",12 "role": "historical polity panel: coordination demand (population, territory, hierarchy), capacity (administration, writing, records, infrastructure), and outcomes",13 "key": "seshat_polaris2026",14 "local_path": "data/raw/seshat_polaris2026/Polaris2026.xlsx",15 "http_status": 200,16 "final_url": "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Polaris2026.xlsx",17 "content_type": "application/octet-stream",18 "retrieved_at_utc": "2026-11-01T07:48:51+00:00",19 "elapsed_s": 0.42,20 "size_bytes": 2899093,21 "sha256": "cf60c9f76eeda6db545521831a9201e65c64d2b74d4aeb55445cd2b564456c41",22 "status": "downloaded"23 },24 "seshat_equinox2020": {25 "dataset": "Seshat Global History Databank — Equinox-2020 snapshot (spreadsheet copy stored in the Polaris repository)",26 "publisher": "Seshat: Global History Databank",27 "release": "Equinox-2020, spreadsheet dated 05.2023 (repository commit 55ca5fbc2b)",28 "url": "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Equinox2020.05.2023.xlsx",29 "landing_page": "https://seshatdatabank.info/data/",30 "license": "MIT (repository LICENSE); original Equinox release on Zenodo (record 6629022) is labelled AGPL-3.0",31 "citation": "Seshat: Global History Databank, Equinox-2020 data release",32 "filename": "Equinox2020.05.2023.xlsx",33 "units": "polity-time rows",34 "role": "robustness: alternative Seshat release",35 "key": "seshat_equinox2020",36 "local_path": "data/raw/seshat_equinox2020/Equinox2020.05.2023.xlsx",37 "http_status": 200,38 "final_url": "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Equinox2020.05.2023.xlsx",39 "content_type": "application/octet-stream",40 "retrieved_at_utc": "2026-11-01T07:48:51+00:00",41 "elapsed_s": 0.32,42 "size_bytes": 1720038,43 "sha256": "7964d74c3ae3a24775323ef61a101ed3ca14ed0d3c47d606b3ce5e28e64968be",44 "status": "downloaded"45 },46 "seshat_equinox_continuous_polities": {47 "dataset": "Seshat Databank: Equinox Release with Culturally and Institutionally Continuous Polities (Timescale SM data)",48 "publisher": "Seshat / Zenodo record 8120128",49 "release": "Zenodo 8120128 (2023-07-06)",50 "url": "https://zenodo.org/api/records/8120128/files/Timescale.SM_Data.xlsx/content",51 "landing_page": "https://zenodo.org/records/8120128",52 "license": "CC-BY-4.0",53 "citation": "Zenodo record 8120128 (Seshat Equinox release with continuous polities), DOI 10.5281/zenodo.8120128",54 "filename": "Timescale.SM_Data.xlsx",55 "units": "polity sequences with start/end dates",56 "role": "polity continuity / sequence boundaries (candidate for event definitions)",57 "key": "seshat_equinox_continuous_polities",58 "local_path": "data/raw/seshat_equinox_continuous_polities/Timescale.SM_Data.xlsx",59 "http_status": 200,60 "final_url": "https://zenodo.org/api/records/8120128/files/Timescale.SM_Data.xlsx/content",61 "content_type": "application/octet-stream, application/octet-stream",62 "retrieved_at_utc": "2026-11-01T07:49:02+00:00",63 "elapsed_s": 0.77,64 "size_bytes": 70197,65 "sha256": "4eb6c1a72de9a96da6c8ffd877f421f41b268ab93b08db1f27b617d1d038b8bc",66 "status": "downloaded"67 },68 "maddison_2023_xlsx": {69 "dataset": "Maddison Project Database 2023",70 "publisher": "Groningen Growth and Development Centre, University of Groningen",71 "release": "MPD 2023 (Bolt & van Zanden 2024)",72 "url": "https://dataverse.nl/api/access/datafile/421302",73 "landing_page": "https://www.rug.nl/ggdc/historicaldevelopment/maddison/releases/maddison-project-database-2023",74 "license": "Free for academic use with citation (GGDC terms); check landing page",75 "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.",76 "filename": "mpd2023_web.xlsx",77 "units": "country-year; GDP per capita in 2011 international USD; population in thousands",78 "role": "modern/long-run economic outcomes and population (country-year panel; NOT mapped onto ancient polities)",79 "key": "maddison_2023_xlsx",80 "local_path": "data/raw/maddison_2023_xlsx/mpd2023_web.xlsx",81 "http_status": 200,82 "final_url": "https://objectstore.surf.nl/store/10.34894/INZBF2/18f1947b695-c2971390baa0?response-content-disposition=attachment%3B%20filename%2A%3DUTF-8%27%27mpd2023_web.xlsx&response-content-type=application%2Fvnd.openxmlformats-officedocument.spreadsheetml.sheet&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20261101T074852Z&X-Amz-SignedHeaders=host&X-Amz-Credential=bf79a78ef3bb4505a9f98459f8a454ad%2F20261101%2Fdataverse%2Fs3%2Faws4_request&X-Amz-Expires=3600&X-Amz-Signature=48c8642edc981174906fd2a3374b61b9e781e7abd672d73a5a4b1956a2785419",83 "content_type": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",84 "retrieved_at_utc": "2026-11-01T07:48:53+00:00",85 "elapsed_s": 1.64,86 "size_bytes": 4903804,87 "sha256": "ecc5916ca12789b983fc4be437f8a354bbf4291323605324ac3e0aea4c57cbb6",88 "status": "downloaded"89 },90 "maddison_2023_dta": {91 "dataset": "Maddison Project Database 2023 (Stata file)",92 "publisher": "GGDC",93 "release": "MPD 2023",94 "url": "https://dataverse.nl/api/access/datafile/421303",95 "landing_page": "https://www.rug.nl/ggdc/historicaldevelopment/maddison/releases/maddison-project-database-2023",96 "license": "Free for academic use with citation",97 "citation": "Bolt & van Zanden (2024)",98 "filename": "mpd2023_web.dta",99 "units": "country-year",100 "role": "cross-check of the xlsx parse",101 "key": "maddison_2023_dta",102 "local_path": "data/raw/maddison_2023_dta/mpd2023_web.dta",103 "http_status": 200,104 "final_url": "https://objectstore.surf.nl/store/10.34894/INZBF2/18f1947b459-7fbdbbff0a80?response-content-disposition=attachment%3B%20filename%2A%3DUTF-8%27%27maddison2023_web.dta&response-content-type=application%2Fx-stata-14&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20261101T074854Z&X-Amz-SignedHeaders=host&X-Amz-Credential=bf79a78ef3bb4505a9f98459f8a454ad%2F20261101%2Fdataverse%2Fs3%2Faws4_request&X-Amz-Expires=3600&X-Amz-Signature=343a3db7b4ed4a49e9b82cd1801b2267f8975b938f281e12e511fe155367d84c",105 "content_type": "application/x-stata-14",106 "retrieved_at_utc": "2026-11-01T07:48:55+00:00",107 "elapsed_s": 1.79,108 "size_bytes": 10892389,109 "sha256": "2bc62ccbd795d4d330ef9ead6dc29c39e956922b43264640eba52d2c244841cb",110 "status": "downloaded"111 },112 "dplace_ea_v3_3": {113 "dataset": "D-PLACE dataset derived from Murdock et al. 1999 'Ethnographic Atlas' (CLDF)",114 "publisher": "D-PLACE (Kirby et al. 2016) / GitHub D-PLACE/dplace-dataset-ea",115 "release": "v3.3 (2025-12-19)",116 "url": "https://api.github.com/repos/D-PLACE/dplace-dataset-ea/zipball/v3.3",117 "landing_page": "https://d-place.org/",118 "license": "CC BY-NC 4.0",119 "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).",120 "filename": "dplace-dataset-ea-v3.3.zip",121 "units": "one row per society (~1,290 societies expected per documentation; actual count computed in Phase 2); coded categorical variables EA001-EA114 + environmental",122 "role": "ethnographic cross-section: political integration (EA033), jurisdictional hierarchy, settlement size (EA031), class stratification; Galton's problem handled with language family / region",123 "key": "dplace_ea_v3_3",124 "local_path": "data/raw/dplace_ea_v3_3/dplace-dataset-ea-v3.3.zip",125 "http_status": 200,126 "final_url": "https://codeload.github.com/D-PLACE/dplace-dataset-ea/legacy.zip/refs/tags/v3.3",127 "content_type": "application/zip",128 "retrieved_at_utc": "2026-11-01T07:49:03+00:00",129 "elapsed_s": 1.36,130 "size_bytes": 7039773,131 "sha256": "9ec031e011019952f53c633e8421792e7ab88a2ba1fea93027b74272c3ee2dbb",132 "status": "downloaded"133 },134 "vdem_v16_rdata": {135 "dataset": "V-Dem Country-Year Dataset v16 (vdemdata R package copy)",136 "publisher": "Varieties of Democracy Institute, University of Gothenburg (official GitHub package vdeminstitute/vdemdata)",137 "release": "v16 (package commit f4dd26922e, 2026-03-17 'v16 release')",138 "url": "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/vdem.RData",139 "landing_page": "https://www.v-dem.net/data/the-v-dem-dataset/",140 "license": "V-Dem data: free for non-commercial use with citation (V-Dem terms of use); package GPL-3",141 "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)",142 "filename": "vdem_v16.RData",143 "units": "country-year, 1789-2025 (to be verified)",144 "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",145 "key": "vdem_v16_rdata",146 "local_path": "data/raw/vdem_v16_rdata/vdem_v16.RData",147 "http_status": 200,148 "final_url": "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/vdem.RData",149 "content_type": "application/octet-stream",150 "retrieved_at_utc": "2026-11-01T07:48:56+00:00",151 "elapsed_s": 0.72,152 "size_bytes": 33878255,153 "sha256": "39b412d39a061c18f20c98e4ad4d6355b05a0441df31be4ee9aec420dc3d95ea",154 "status": "downloaded"155 },156 "vdem_v16_codebook": {157 "dataset": "V-Dem codebook (R object)",158 "publisher": "V-Dem Institute",159 "release": "v16",160 "url": "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/codebook.RData",161 "landing_page": "https://www.v-dem.net/data/the-v-dem-dataset/",162 "license": "GPL-3 (package)",163 "citation": "Coppedge et al. (2026) V-Dem Codebook v16",164 "filename": "vdem_v16_codebook.RData",165 "units": "variable metadata",166 "role": "data dictionary for V-Dem",167 "key": "vdem_v16_codebook",168 "local_path": "data/raw/vdem_v16_codebook/vdem_v16_codebook.RData",169 "http_status": 200,170 "final_url": "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/codebook.RData",171 "content_type": "application/octet-stream",172 "retrieved_at_utc": "2026-11-01T07:48:56+00:00",173 "elapsed_s": 0.12,174 "size_bytes": 148633,175 "sha256": "2840d879cb9071b1f742f5f18c5373518a586ac90454b58dbf5f4309077f0700",176 "status": "downloaded"177 },178 "glottolog_cldf_languages": {179 "dataset": "Glottolog CLDF languages table (language family for Galton controls)",180 "publisher": "Glottolog (Hammarström, Forkel, Haspelmath, Bank), MPI-EVA",181 "release": "glottolog-cldf v5.3 (2026-03-02)",182 "url": "https://raw.githubusercontent.com/glottolog/glottolog-cldf/v5.3/cldf/languages.csv",183 "landing_page": "https://glottolog.org/",184 "license": "CC BY 4.0",185 "citation": "Hammarström, H., Forkel, R., Haspelmath, M. & Bank, S. Glottolog 5.3. Leipzig: Max Planck Institute for Evolutionary Anthropology. https://glottolog.org",186 "filename": "glottolog_v5.3_languages.csv",187 "units": "one row per languoid; Family_ID",188 "role": "map D-PLACE Glottocodes to language families (non-independence control)",189 "key": "glottolog_cldf_languages",190 "local_path": "data/raw/glottolog_cldf_languages/glottolog_v5.3_languages.csv",191 "http_status": 200,192 "final_url": "https://raw.githubusercontent.com/glottolog/glottolog-cldf/v5.3/cldf/languages.csv",193 "content_type": "text/plain; charset=utf-8",194 "retrieved_at_utc": "2026-11-01T08:06:56+00:00",195 "elapsed_s": 0.48,196 "size_bytes": 2477017,197 "sha256": "1a50a393bc81568b656f9522be18aa4f80f38e94309ba6c863d583234adfbb89",198 "status": "downloaded"199 }200}