{ "api_version": "1.0", "base_url": "https://taehyun-lim.github.io/krpoltext", "generated_at": "2026-04-20T00:41:57Z", "package": { "name": "krpoltext", "version": "0.2.0", "github": "https://github.com/taehyun-lim/krpoltext", "paper_doi": "10.1038/s41597-025-05220-4" }, "resources": [ { "name": "campaign_booklet", "file": "sk_election_campaign_booklet_v2022.csv", "version": "v2022", "format": "csv", "encoding": "UTF-8", "size_bytes": 756245336, "sha256": "6ce6f40f5358829b167109d9ca9195e5089d2c6d05a61ad1c1925e424f55021d", "download_url": "https://osf.io/download/6ybj8/", "managed": true, "n_rows": 49678, "n_cols": 31, "description": "Original krpoltext campaign booklet corpus artifact covering 49,678 document rows from South Korean presidential, National Assembly, and local elections, 2000-2022.", "time_coverage": "2000-2022", "schema_url": "data/schema/campaign_booklet.json", "license": "CC BY-NC-ND 4.0", "variant": "original", "default_for_package": true, "recommended_for": "General corpus analysis and backward-compatible workflows." }, { "name": "campaign_booklet", "file": "sk_election_campaign_booklet_v2022.parquet", "version": "v2022", "format": "parquet", "encoding": "UTF-8", "size_bytes": 406524268, "sha256": "a291a887d157963cffcffbe2c1ad60333222dd479bf4b01e90cec3a28d5c19a6", "download_url": "https://osf.io/download/pxg2k/", "managed": true, "n_rows": 49678, "n_cols": 31, "description": "Original krpoltext campaign booklet corpus artifact covering 49,678 document rows from South Korean presidential, National Assembly, and local elections, 2000-2022.", "time_coverage": "2000-2022", "schema_url": "data/schema/campaign_booklet.json", "license": "CC BY-NC-ND 4.0", "variant": "original", "default_for_package": true, "recommended_for": "General corpus analysis and backward-compatible workflows." }, { "name": "campaign_booklet", "file": "sk_election_campaign_booklet_enriched_v2022.csv", "version": "v2022", "format": "csv", "encoding": "UTF-8", "size_bytes": 760045361, "sha256": "08779d4c27a02635c7bf08a332170ac0a5bf1295e825e3b29061c62f95598586", "download_url": "https://osf.io/download/69e3eec5352dbdd881fd8d7b/", "managed": true, "n_rows": 49678, "n_cols": 37, "description": "Enriched campaign booklet artifact using the same document-row universe as the original CSV source, with conservative NEC linkage fields such as 'huboid', 'sg_id', and 'sg_typecode' added to improve interoperability with kr-elections-mcp and related NEC-aligned workflows.", "time_coverage": "2000-2022", "schema_url": "data/schema/campaign_booklet_enriched.json", "license": "CC BY-NC-ND 4.0", "variant": "enriched", "default_for_package": false, "recommended_for": "NEC-aligned workflows, kr-elections-mcp, and linkage-aware joins." }, { "name": "campaign_booklet", "file": "sk_election_campaign_booklet_enriched_v2022.parquet", "version": "v2022", "format": "parquet", "encoding": "UTF-8", "size_bytes": 406231949, "sha256": "d8901cd2cebef30116f8865847727bb10855478ee556bc0dcfb5a04e838ad8f4", "download_url": "https://osf.io/download/69e3ee72a0e06b0928fd8ae2/", "managed": true, "n_rows": 49678, "n_cols": 37, "description": "Enriched campaign booklet artifact using the same document-row universe as the original CSV source, with conservative NEC linkage fields such as 'huboid', 'sg_id', and 'sg_typecode' added to improve interoperability with kr-elections-mcp and related NEC-aligned workflows.", "time_coverage": "2000-2022", "schema_url": "data/schema/campaign_booklet_enriched.json", "license": "CC BY-NC-ND 4.0", "variant": "enriched", "default_for_package": false, "recommended_for": "NEC-aligned workflows, kr-elections-mcp, and linkage-aware joins." }, { "name": "party_statements", "file": "sk_party_statements_v2022.csv", "version": "v2022", "format": "csv", "encoding": "UTF-8", "size_bytes": 740785920, "sha256": "60874e7c44d851c9cfc0892d70f6ef9ff9fb3993a5324963297ca4eabd4868e4", "download_url": "https://osf.io/download/8u2ah/", "managed": true, "n_rows": 83201, "n_cols": 9, "description": "Official statements from party spokespersons and minutes from daily leadership meetings of South Korea's two major parties (Conservative and Progressive), covering 2003 to 2022. 83,201 total entries (35,115 conservative + 48,086 progressive). Parsed using the khaiii Korean morphological analyzer.", "time_coverage": "2003-2022", "schema_url": "data/schema/party_statements.json", "license": "CC BY-NC-ND 4.0" }, { "name": "party_statements", "file": "sk_party_statements_v2022.parquet", "version": "v2022", "format": "parquet", "encoding": "UTF-8", "size_bytes": 393216464, "sha256": "cee8a49adbe90f96ee4e2b45b6d84c433e5eb9ebb4849cfc979f6a19c57378ea", "download_url": "https://osf.io/download/8cjxu/", "managed": true, "n_rows": 83201, "n_cols": 9, "description": "Official statements from party spokespersons and minutes from daily leadership meetings of South Korea's two major parties (Conservative and Progressive), covering 2003 to 2022. 83,201 total entries (35,115 conservative + 48,086 progressive). Parsed using the khaiii Korean morphological analyzer.", "time_coverage": "2003-2022", "schema_url": "data/schema/party_statements.json", "license": "CC BY-NC-ND 4.0" } ] }