{ "schema_version": "platform-qazlake-snapshot-v1", "generated_at": "2026-07-14T15:20:44Z", "generated_by": "tools/platform_data_bridge.py", "source": { "repository": "https://github.com/belilovsky/qazlake-api", "revision": "97ad293b3aaa864792d34d75c3060c6e2243e023", "contract_export": "collectors.registry --contracts --json", "sensitive_fields_excluded": [ "api_url", "error_message", "host", "notes", "payload", "raw", "storage_url", "url" ] }, "counts": { "sources": 114, "priority_p1": 36, "public_yes": 93, "public_review": 21, "pii_high": 1, "corpus_sources": 38, "consumer_profiles": 7, "import_items": 38, "collector_ready": 30, "already_materialized": 8 }, "categories": [ { "category": "nlp", "count": 28 }, { "category": "hydro", "count": 24 }, { "category": "media", "count": 13 }, { "category": "geo", "count": 12 }, { "category": "international", "count": 9 }, { "category": "satellite", "count": 9 }, { "category": "finance", "count": 5 }, { "category": "climate", "count": 4 }, { "category": "bio", "count": 2 }, { "category": "events", "count": 2 }, { "category": "seismology", "count": 2 }, { "category": "statistics", "count": 2 }, { "category": "gov-open-data", "count": 1 }, { "category": "legal", "count": 1 } ], "consumer_profiles": [ { "profile_id": "events_central_asia", "label": "Events / Central Asia", "description": "Структурированные событийные наборы по протестам и политическому насилию.", "filters": { "consumer": "event_dataset", "region": "central_asia" }, "count": 2, "policy_summary": { "total": 2, "public_yes": 0, "public_review": 2, "public_no": 0 } }, { "profile_id": "legal_ru_cis", "label": "Legal / RU CIS", "description": "Юридические и квазиюридические корпуса на русском для формулировок и цитирования.", "filters": { "consumer": "legal_corpus", "language": "ru" }, "count": 2, "policy_summary": { "total": 2, "public_yes": 1, "public_review": 1, "public_no": 0 } }, { "profile_id": "news_cis_monitoring", "label": "News / CIS Monitoring", "description": "Новостные корпуса для медиа-мониторинга Казахстана и русскоязычного контура.", "filters": { "consumer": "news_corpus" }, "count": 7, "policy_summary": { "total": 7, "public_yes": 4, "public_review": 3, "public_no": 0 } }, { "profile_id": "parliament_global", "label": "Parliament / Global", "description": "Парламентские корпуса и политико-повесточный слой.", "filters": { "consumer": "parliament_corpus" }, "count": 2, "policy_summary": { "total": 2, "public_yes": 1, "public_review": 1, "public_no": 0 } }, { "profile_id": "quotes_kazakhstan_official", "label": "Quotes / Kazakhstan Official", "description": "Официальные тексты Казахстана для баз цитат и выдержек.", "filters": { "consumer": "quote_base", "region": "kazakhstan", "official_only": true }, "count": 6, "policy_summary": { "total": 6, "public_yes": 4, "public_review": 2, "public_no": 0 } }, { "profile_id": "theses_kazakhstan_official", "label": "Theses / Kazakhstan Official", "description": "Тезисные корпуса официальной риторики Казахстана.", "filters": { "consumer": "thesis_base", "region": "kazakhstan", "official_only": true }, "count": 6, "policy_summary": { "total": 6, "public_yes": 4, "public_review": 2, "public_no": 0 } }, { "profile_id": "translation_kk_central_asia", "label": "Translation KK / Central Asia", "description": "Параллельные и близкие к переводу корпуса для KZ/UZ/регионального MT.", "filters": { "consumer": "translation", "language": "kk" }, "count": 2, "policy_summary": { "total": 2, "public_yes": 1, "public_review": 1, "public_no": 0 } } ], "import_plan": [ { "source_id": "events-001", "name": "ACLED Central Asia and the Caucasus", "priority": "P1", "category": "events", "content_kind": "event_dataset", "consumer_tags": [ "event_dataset", "political_discourse" ], "status": "collector_ready", "loader": "collector_events_corpora.py", "mode": "api_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "events-002", "name": "Central Asia Protest Tracker", "priority": "P2", "category": "events", "content_kind": "event_dataset", "consumer_tags": [ "event_dataset" ], "status": "collector_ready", "loader": "collector_events_corpora.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "legal-001", "name": "RusLawOD", "priority": "P2", "category": "legal", "content_kind": "legal_corpus", "consumer_tags": [ "legal_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-001", "name": "PSSR (сигналы раннего предупреждения)", "priority": "P1", "category": "media", "content_kind": "event_dataset", "consumer_tags": [ "event_dataset" ], "status": "already_materialized", "loader": "sql/migrate_pssr.sql", "mode": "dblink_migration", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-002", "name": "QazPolit (политические персоны)", "priority": "P1", "category": "media", "content_kind": "event_dataset", "consumer_tags": [ "event_dataset", "political_discourse" ], "status": "already_materialized", "loader": "sql/migrate_qazpolit.sql", "mode": "dblink_migration", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-003", "name": "Constitution RAG (Конституция КЗ)", "priority": "P1", "category": "media", "content_kind": "legal_corpus", "consumer_tags": [ "legal_corpus", "quote_base", "thesis_base", "official_rhetoric" ], "status": "already_materialized", "loader": "scripts/migrate_constitution.sh", "mode": "json_to_sql", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "media-005", "name": "Echo Sounder (GDELT/NewsData/RSS)", "priority": "P1", "category": "media", "content_kind": "news_corpus", "consumer_tags": [ "news_corpus" ], "status": "already_materialized", "loader": "existing_qazlake_sync", "mode": "project_sync", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-006", "name": "OrtCom (пресс-релизы госорганов)", "priority": "P1", "category": "media", "content_kind": "speech_text", "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base" ], "status": "already_materialized", "loader": "existing_qazlake_sync", "mode": "project_sync", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "media-007", "name": "Total KZ (казахстанские СМИ)", "priority": "P1", "category": "media", "content_kind": "news_corpus", "consumer_tags": [ "news_corpus" ], "status": "already_materialized", "loader": "existing_qazlake_sync", "mode": "dblink_sync", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-008", "name": "NPA Collector — zan.gov.kz (НПА)", "priority": "P1", "category": "media", "content_kind": "legal_corpus", "consumer_tags": [ "legal_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "status": "already_materialized", "loader": "existing_qazlake_sync", "mode": "dblink_sync", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "media-010", "name": "Tokaev Module (тезисы Президента)", "priority": "P1", "category": "media", "content_kind": "speech_text", "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base" ], "status": "already_materialized", "loader": "existing_qazlake_sync", "mode": "project_sync", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "media-012", "name": "Nursultan Nazarbayev Speech Dataset (Kaggle)", "priority": "P2", "category": "media", "content_kind": "speech_audio", "consumer_tags": [ "official_rhetoric", "speech_audio", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "media-013", "name": "Н.А. Назарбаев — speeches interviews and addresses", "priority": "P2", "category": "media", "content_kind": "speech_text", "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-001", "name": "KSC2 — Kazakh Speech Corpus 2", "priority": "P1", "category": "nlp", "content_kind": "speech_audio", "consumer_tags": [ "speech_audio", "asr_dataset", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-002", "name": "KazParC — Kazakh Parallel Corpus", "priority": "P1", "category": "nlp", "content_kind": "parallel_corpus", "consumer_tags": [ "parallel_corpus", "translation", "official_rhetoric", "speech_text", "general_corpus", "quote_base", "thesis_base" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-005", "name": "CC-100 — Kazakh (kk)", "priority": "P2", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-006", "name": "Leipzig Kazakh Web Corpora 2019", "priority": "P2", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-007", "name": "KSD — Kazakh Speech Dataset (OpenSLR SLR140)", "priority": "P3", "category": "nlp", "content_kind": "speech_audio", "consumer_tags": [ "speech_audio", "asr_dataset", "general_corpus", "speech_synthesis" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-008", "name": "KazakhTTS2 — Text-to-Speech Corpus", "priority": "P3", "category": "nlp", "content_kind": "speech_audio", "consumer_tags": [ "speech_audio", "speech_synthesis", "general_corpus", "asr_dataset" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-009", "name": "KazNERD — Named Entity Recognition", "priority": "P3", "category": "nlp", "content_kind": "news_corpus", "consumer_tags": [ "ner_dataset", "news_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-010", "name": "KazSAnDRA — Sentiment Analysis Dataset", "priority": "P3", "category": "nlp", "content_kind": "sentiment_dataset", "consumer_tags": [ "sentiment_dataset", "general_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-011", "name": "Kazakh Instruction v2 (LLaMA fine-tuning)", "priority": "P3", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-012", "name": "Multidomain Kazakh Dataset", "priority": "P3", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-013", "name": "National Corpus of Kazakh", "priority": "P3", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-015", "name": "KazQAD — Kazakh Question Answering Dataset", "priority": "P3", "category": "nlp", "content_kind": "qa_corpus", "consumer_tags": [ "qa_corpus", "general_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-016", "name": "Kazakhstani and Russian News Corpus (Mendeley)", "priority": "P1", "category": "nlp", "content_kind": "news_corpus", "consumer_tags": [ "news_corpus", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-017", "name": "Lenta.Ru News Dataset", "priority": "P2", "category": "nlp", "content_kind": "news_corpus", "consumer_tags": [ "news_corpus", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-018", "name": "russian_news_corpus", "priority": "P2", "category": "nlp", "content_kind": "news_corpus", "consumer_tags": [ "news_corpus", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-019", "name": "Uzbek-Kazakh Parallel Corpus", "priority": "P2", "category": "nlp", "content_kind": "parallel_corpus", "consumer_tags": [ "parallel_corpus", "translation", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-020", "name": "ISSAI NLP Datasets — Nazarbayev University", "priority": "P2", "category": "nlp", "content_kind": "speech_audio", "consumer_tags": [ "speech_audio", "ner_dataset", "sentiment_dataset", "qa_corpus", "general_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "status": "collector_ready", "loader": "collector_issai.py", "mode": "catalog_metadata", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-021", "name": "QazCorpus — National Corpus of Kazakh Language", "priority": "P2", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_kazcorpus.py", "mode": "catalog_metadata", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-022", "name": "Tajik Web Corpus", "priority": "P2", "category": "nlp", "content_kind": "news_corpus", "consumer_tags": [ "general_corpus", "news_corpus" ], "status": "collector_ready", "loader": "collector_hf_datasets.py", "mode": "hf_metadata_or_snapshot", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" }, { "source_id": "nlp-023", "name": "Manifesto Corpus / ManifestoBERTa", "priority": "P2", "category": "nlp", "content_kind": "political_discourse", "consumer_tags": [ "political_discourse", "thesis_base", "official_rhetoric", "general_corpus", "quote_base" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-024", "name": "ParlaMint 5.0", "priority": "P2", "category": "nlp", "content_kind": "parliament_corpus", "consumer_tags": [ "parliament_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "attribution" }, { "source_id": "nlp-025", "name": "ParlaCAP", "priority": "P2", "category": "nlp", "content_kind": "parliament_corpus", "consumer_tags": [ "parliament_corpus", "official_rhetoric", "thesis_base", "political_discourse", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-026", "name": "Corpus of Political Speeches (HKBU)", "priority": "P2", "category": "nlp", "content_kind": "speech_text", "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base", "political_discourse", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-027", "name": "UzbekPOS — Multi-domain POS Dataset", "priority": "P2", "category": "nlp", "content_kind": "pos_dataset", "consumer_tags": [ "pos_dataset", "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": true, "public_allowed": "review", "redistribution_allowed": "review" }, { "source_id": "nlp-028", "name": "Uzbek-Corpus-Sample", "priority": "P3", "category": "nlp", "content_kind": "general_corpus", "consumer_tags": [ "general_corpus" ], "status": "collector_ready", "loader": "collector_nlp_web.py", "mode": "remote_metadata_or_download", "review_required": false, "public_allowed": "yes", "redistribution_allowed": "yes" } ], "sources": [ { "source_id": "bio-001", "name": "GBIF — Global Biodiversity Information Facility", "owner": "GBIF", "category": "bio", "source_type": "api", "formats": [ "JSON", "CSV", "DwC-A" ], "license": "CC-BY", "attribution": "GBIF", "priority": "P2", "scope_tags": [ "bio", "environment", "lakes" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "bio-002", "name": "Threatened Species — Kazakhstan (Mendeley)", "owner": "Mendeley Data", "category": "bio", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "CC-BY", "attribution": "Mendeley Data", "priority": "P3", "scope_tags": [ "bio", "environment" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "climate-001", "name": "ERA5 (World Bank Climate Knowledge Portal)", "owner": "World Bank / ECMWF", "category": "climate", "source_type": "download", "formats": [ "NetCDF", "CSV" ], "license": "CC-BY", "attribution": "World Bank / ECMWF", "priority": "P1", "scope_tags": [ "climate", "hydro", "lakes" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "climate-002", "name": "AirData.kz", "owner": "Казгидромет / РЦЭО", "category": "climate", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "gov-open", "attribution": "Казгидромет / РЦЭО", "priority": "P2", "scope_tags": [ "environment", "climate" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 3600, "cache_ttl_s": 7200, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "climate-003", "name": "CHELSA — Climatologies at High Resolution", "owner": "Uni Basel", "category": "climate", "source_type": "download", "formats": [ "NetCDF", "GeoTIFF" ], "license": "CC-BY-4.0", "attribution": "Uni Basel", "priority": "P2", "scope_tags": [ "climate" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "climate-004", "name": "NEX-GDDP CMIP6", "owner": "NASA NEX", "category": "climate", "source_type": "download", "formats": [ "NetCDF" ], "license": "open", "attribution": "NASA NEX", "priority": "P2", "scope_tags": [ "climate", "hydro" ], "region": "central_asia", "region_tags": [ "central_asia" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "events-001", "name": "ACLED Central Asia and the Caucasus", "owner": "ACLED", "category": "events", "source_type": "api", "formats": [ "JSON", "CSV" ], "license": "research-review", "attribution": "ACLED", "priority": "P1", "scope_tags": [ "events", "event_dataset", "central_asia", "kazakhstan" ], "consumer_tags": [ "event_dataset", "political_discourse" ], "region": "central_asia", "region_tags": [ "central_asia", "kazakhstan" ], "content_kind": "event_dataset", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "events-002", "name": "Central Asia Protest Tracker", "owner": "Oxus Society", "category": "events", "source_type": "download", "formats": [ "XLSX", "CSV" ], "license": "research-review", "attribution": "Oxus Society", "priority": "P2", "scope_tags": [ "events", "event_dataset", "central_asia", "kazakhstan" ], "consumer_tags": [ "event_dataset" ], "region": "central_asia", "region_tags": [ "central_asia", "kazakhstan" ], "content_kind": "event_dataset", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 7776000, "cache_ttl_s": 15552000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "finance-001", "name": "Национальный банк РК — open data", "owner": "НБК", "category": "finance", "source_type": "api", "formats": [ "JSON", "CSV", "XLSX" ], "license": "gov-open", "attribution": "НБК", "priority": "P1", "scope_tags": [ "finance", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "finance-002", "name": "Госзакупки goszakup.gov.kz", "owner": "МФ РК", "category": "finance", "source_type": "api", "formats": [ "JSON", "CSV" ], "license": "gov-open", "attribution": "МФ РК", "priority": "P1", "scope_tags": [ "finance", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "finance-003", "name": "API Министерства финансов РК (ecc.kz)", "owner": "МФ РК", "category": "finance", "source_type": "api", "formats": [ "JSON", "XML" ], "license": "gov-open", "attribution": "МФ РК", "priority": "P1", "scope_tags": [ "finance", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "finance-004", "name": "IMF Data", "owner": "IMF", "category": "finance", "source_type": "api", "formats": [ "JSON", "SDMX 2.1/3.0" ], "license": "open", "attribution": "IMF", "priority": "P2", "scope_tags": [ "finance", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 7776000, "cache_ttl_s": 15552000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "finance-005", "name": "Asian Development Bank — Kazakhstan Key Indicators", "owner": "ADB", "category": "finance", "source_type": "download", "formats": [ "XLSX", "CSV" ], "license": "CC-BY-3.0", "attribution": "ADB", "priority": "P2", "scope_tags": [ "finance", "socioeconomic" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-001", "name": "Геопортал НИПД map.gov.kz (NSDI)", "owner": "КартГео РК", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS", "WMTS", "WFS", "WCS", "GeoJSON" ], "license": "gov-open", "attribution": "КартГео РК", "priority": "P1", "scope_tags": [ "geo", "lakes", "hydro" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-002", "name": "geo-boundaries-kz (GitHub)", "owner": "open-data-kazakhstan", "category": "geo", "source_type": "download", "formats": [ "GeoJSON", "TopoJSON", "Shapefile", "SVG", "CSV" ], "license": "open", "attribution": "open-data-kazakhstan", "priority": "P1", "scope_tags": [ "geo", "lakes" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-003", "name": "OpenStreetMap Overpass API", "owner": "OSM Contributors", "category": "geo", "source_type": "api", "formats": [ "GeoJSON", "XML" ], "license": "ODbL", "attribution": "OSM Contributors", "priority": "P1", "scope_tags": [ "geo", "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 300, "cache_ttl_s": 3600, "public_allowed": "yes", "redistribution_allowed": "share_alike", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-004", "name": "RGI/GLIMS — Randolph Glacier Inventory", "owner": "NSIDC / GLIMS", "category": "geo", "source_type": "download", "formats": [ "Shapefile", "GeoJSON" ], "license": "CC-BY-4.0", "attribution": "NSIDC / GLIMS", "priority": "P3", "scope_tags": [ "hydro", "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-005", "name": "WMS Атырауской области", "owner": "Акимат Атырауской обл.", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS" ], "license": "gov-open", "attribution": "Акимат Атырауской обл.", "priority": "P3", "scope_tags": [ "geo", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-006", "name": "WMS Жамбылской области", "owner": "Акимат Жамбылской обл.", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS" ], "license": "gov-open", "attribution": "Акимат Жамбылской обл.", "priority": "P3", "scope_tags": [ "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-007", "name": "WMS г. Шымкент", "owner": "Акимат г. Шымкент", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS" ], "license": "gov-open", "attribution": "Акимат г. Шымкент", "priority": "P3", "scope_tags": [ "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-008", "name": "WMS Актюбинской области", "owner": "Акимат Актюбинской обл.", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS" ], "license": "gov-open", "attribution": "Акимат Актюбинской обл.", "priority": "P3", "scope_tags": [ "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-009", "name": "WMS Павлодарской области", "owner": "Акимат Павлодарской обл.", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS" ], "license": "gov-open", "attribution": "Акимат Павлодарской обл.", "priority": "P3", "scope_tags": [ "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-010", "name": "Геопортал геологии МЭГ РК", "owner": "МЭГ РК", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS", "GeoJSON" ], "license": "gov-open", "attribution": "МЭГ РК", "priority": "P3", "scope_tags": [ "geo", "environment" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-011", "name": "Геопортал геологии (пилот)", "owner": "МЭГ РК", "category": "geo", "source_type": "wms/wfs", "formats": [ "WMS", "GeoJSON" ], "license": "gov-open", "attribution": "МЭГ РК", "priority": "P3", "scope_tags": [ "geo", "environment" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "geo-012", "name": "geokz R-пакет", "owner": "A. Rodionoff (GitHub)", "category": "geo", "source_type": "download", "formats": [ "sf", "Data Frame", "CSV" ], "license": "open", "attribution": "A. Rodionoff (GitHub)", "priority": "P3", "scope_tags": [ "geo", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "gov-001", "name": "Главный портал открытых данных data.egov.kz", "owner": "МЦРиАП РК", "category": "gov-open-data", "source_type": "api", "formats": [ "JSON", "XML", "XLSX" ], "license": "gov-open", "attribution": "МЦРиАП РК", "priority": "P1", "scope_tags": [ "lakes", "hydro", "socioeconomic", "geo", "legal" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-001", "name": "Казгидромет — главный портал", "owner": "Казгидромет", "category": "hydro", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "gov-open", "attribution": "Казгидромет", "priority": "P1", "scope_tags": [ "hydro", "climate", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-002", "name": "Карта гидропостов ecodata.kz", "owner": "Казгидромет", "category": "hydro", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "gov-open", "attribution": "Казгидромет", "priority": "P1", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-003", "name": "Гидрологическая база ecodata.kz", "owner": "Казгидромет", "category": "hydro", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "gov-open", "attribution": "Казгидромет", "priority": "P1", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-004", "name": "Качество поверхностных вод ecodata.kz", "owner": "Казгидромет", "category": "hydro", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "gov-open", "attribution": "Казгидромет", "priority": "P1", "scope_tags": [ "hydro", "environment", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-005", "name": "Государственный водный кадастр", "owner": "Казгидромет", "category": "hydro", "source_type": "download", "formats": [ "PDF", "XLSX" ], "license": "gov-open", "attribution": "Казгидромет", "priority": "P1", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-006", "name": "HydroLAKES", "owner": "McGill / HydroSHEDS", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "GeoJSON" ], "license": "CC-BY-4.0", "attribution": "McGill / HydroSHEDS", "priority": "P1", "scope_tags": [ "lakes", "hydro" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-007", "name": "LakeATLAS", "owner": "McGill / HydroSHEDS", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "GeoJSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "McGill / HydroSHEDS", "priority": "P1", "scope_tags": [ "lakes", "hydro" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-008", "name": "UNEP GEMS/Water — GEMStat", "owner": "UNEP", "category": "hydro", "source_type": "api", "formats": [ "CSV", "JSON" ], "license": "CC-BY", "attribution": "UNEP", "priority": "P2", "scope_tags": [ "environment", "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-009", "name": "SARL — Surface Area of Reservoirs and Lakes", "owner": "Zenodo", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "GeoTIFF", "CSV" ], "license": "CC-BY", "attribution": "Zenodo", "priority": "P2", "scope_tags": [ "lakes", "hydro" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-010", "name": "HydroSHEDS", "owner": "USGS / WWF", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "GeoTIFF", "GeoJSON" ], "license": "CC-BY-4.0", "attribution": "USGS / WWF", "priority": "P2", "scope_tags": [ "hydro", "geo", "lakes" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-011", "name": "CAWater-Info (МКВК)", "owner": "МКВК", "category": "hydro", "source_type": "download", "formats": [ "PDF", "XLSX", "CSV" ], "license": "open", "attribution": "МКВК", "priority": "P2", "scope_tags": [ "hydro", "lakes", "environment" ], "region": "central_asia", "region_tags": [ "central_asia" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-012", "name": "Theia Hydroweb", "owner": "CNES / Theia", "category": "hydro", "source_type": "download", "formats": [ "CSV", "NetCDF" ], "license": "open", "attribution": "CNES / Theia", "priority": "P2", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-013", "name": "G-REALM — Global Reservoir and Lake Monitor", "owner": "USDA / NASA", "category": "hydro", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "open", "attribution": "USDA / NASA", "priority": "P2", "scope_tags": [ "hydro", "lakes" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-014", "name": "GRanD v1.3 — Global Reservoir and Dam Database", "owner": "McGill / Global Dam Watch", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "CSV" ], "license": "CC-BY-4.0", "attribution": "McGill / Global Dam Watch", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-015", "name": "GDAT — Global Dam Tracker", "owner": "Global Dam Watch", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "CSV", "GeoJSON" ], "license": "CC-BY-4.0", "attribution": "Global Dam Watch", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-016", "name": "WGMS — World Glacier Monitoring Service", "owner": "WGMS", "category": "hydro", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "CC-BY", "attribution": "WGMS", "priority": "P3", "scope_tags": [ "hydro", "climate" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-017", "name": "Батиметрия оз. Есик (Mendeley)", "owner": "Mendeley Data", "category": "hydro", "source_type": "download", "formats": [ "GeoTIFF", "CSV" ], "license": "CC-BY-4.0", "attribution": "Mendeley Data", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-018", "name": "57 ледниковых озёр Тянь-Шаня (батиметрия)", "owner": "Frontiers 2023", "category": "hydro", "source_type": "download", "formats": [ "CSV", "GeoTIFF" ], "license": "CC-BY", "attribution": "Frontiers 2023", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-019", "name": "CA-discharge — гидропосты ЦА", "owner": "Zenodo", "category": "hydro", "source_type": "download", "formats": [ "CSV", "NetCDF" ], "license": "CC-BY-4.0", "attribution": "Zenodo", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "region": "central_asia", "region_tags": [ "central_asia" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-020", "name": "Бассейновые шейпфайлы КЗ (Zenodo)", "owner": "Zenodo", "category": "hydro", "source_type": "download", "formats": [ "Shapefile", "GeoJSON" ], "license": "CC-BY", "attribution": "Zenodo", "priority": "P3", "scope_tags": [ "hydro", "geo", "lakes" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-021", "name": "Water Data Portal (GitHub)", "owner": "open-data-kazakhstan", "category": "hydro", "source_type": "download", "formats": [ "GeoJSON", "CSV" ], "license": "open", "attribution": "open-data-kazakhstan", "priority": "P3", "scope_tags": [ "hydro", "lakes" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-022", "name": "Open-data-kazakhstan water-resources", "owner": "open-data-kazakhstan", "category": "hydro", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "open", "attribution": "open-data-kazakhstan", "priority": "P3", "scope_tags": [ "hydro", "socioeconomic" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-023", "name": "Water Base Казгидрогеология (подземные воды)", "owner": "Казгидрогеология", "category": "hydro", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "gov-open", "attribution": "Казгидрогеология", "priority": "P3", "scope_tags": [ "hydro", "environment" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "hydro-024", "name": "GLOBGM v1.0 — глобальная модель подземных вод", "owner": "Utrecht / PCR-GLOBWB", "category": "hydro", "source_type": "gee", "formats": [ "NetCDF", "GeoTIFF" ], "license": "CC-BY-4.0", "attribution": "Utrecht / PCR-GLOBWB", "priority": "P3", "scope_tags": [ "hydro", "environment" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-001", "name": "World Bank Kazakhstan", "owner": "World Bank", "category": "international", "source_type": "api", "formats": [ "JSON", "CSV", "XLSX" ], "license": "CC-BY-4.0", "attribution": "World Bank", "priority": "P1", "scope_tags": [ "socioeconomic", "environment", "hydro" ], "region": "kazakhstan", "region_tags": [ "kazakhstan", "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-002", "name": "FAO AQUASTAT", "owner": "FAO", "category": "international", "source_type": "download", "formats": [ "CSV", "XLSX", "JSON" ], "license": "CC-BY", "attribution": "FAO", "priority": "P3", "scope_tags": [ "hydro", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-003", "name": "UNECE — Экологические отчёты КЗ", "owner": "UNECE", "category": "international", "source_type": "download", "formats": [ "PDF", "XLSX" ], "license": "open", "attribution": "UNECE", "priority": "P3", "scope_tags": [ "environment", "socioeconomic" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-004", "name": "Global Water Partnership", "owner": "GWP", "category": "international", "source_type": "download", "formats": [ "PDF", "XLSX" ], "license": "open", "attribution": "GWP", "priority": "P3", "scope_tags": [ "hydro", "environment" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-005", "name": "data.gov USA — Kazakhstan datasets", "owner": "NOAA / US Gov", "category": "international", "source_type": "download", "formats": [ "CSV", "NetCDF" ], "license": "open", "attribution": "NOAA / US Gov", "priority": "P3", "scope_tags": [ "climate", "hydro" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-006", "name": "Dateno KZ — агрегатор датасетов", "owner": "Dateno", "category": "international", "source_type": "download", "formats": [ "CSV", "JSON", "XLSX" ], "license": "open", "attribution": "Dateno", "priority": "P3", "scope_tags": [ "socioeconomic", "geo", "hydro" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-007", "name": "Data360 World Bank Kazakhstan", "owner": "World Bank", "category": "international", "source_type": "api", "formats": [ "JSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "World Bank", "priority": "P3", "scope_tags": [ "socioeconomic", "finance" ], "region": "kazakhstan", "region_tags": [ "kazakhstan", "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-008", "name": "SDG 6 Data Kazakhstan", "owner": "UN-Water", "category": "international", "source_type": "download", "formats": [ "CSV", "XLSX" ], "license": "open", "attribution": "UN-Water", "priority": "P3", "scope_tags": [ "environment", "hydro" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "intl-009", "name": "Dateno — stat.gov.kz каталог", "owner": "Dateno", "category": "international", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "open", "attribution": "Dateno", "priority": "P3", "scope_tags": [ "socioeconomic", "statistics" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "legal-001", "name": "RusLawOD", "owner": "IRL / Hugging Face", "category": "legal", "source_type": "download", "formats": [ "JSON", "txt" ], "license": "research-review", "attribution": "IRL / Hugging Face", "priority": "P2", "scope_tags": [ "legal", "legal_corpus", "official_rhetoric", "quote_base", "thesis_base", "lang_ru", "cis" ], "consumer_tags": [ "legal_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "languages": [ "ru" ], "region": "cis", "region_tags": [ "cis" ], "content_kind": "legal_corpus", "official_rhetoric": true, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-001", "name": "PSSR (сигналы раннего предупреждения)", "owner": "QazLake", "category": "media", "source_type": "download", "formats": [ "JSON" ], "license": "proprietary", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media" ], "consumer_tags": [ "event_dataset" ], "content_kind": "event_dataset", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-002", "name": "QazPolit (политические персоны)", "owner": "QazLake", "category": "media", "source_type": "download", "formats": [ "JSON" ], "license": "proprietary", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media" ], "consumer_tags": [ "event_dataset", "political_discourse" ], "content_kind": "event_dataset", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-003", "name": "Constitution RAG (Конституция КЗ)", "owner": "QazLake", "category": "media", "source_type": "download", "formats": [ "JSON", "PDF" ], "license": "gov-open", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "legal", "legal_corpus", "quote_base", "thesis_base", "official_rhetoric", "lang_kk", "lang_ru", "kazakhstan" ], "consumer_tags": [ "legal_corpus", "quote_base", "thesis_base", "official_rhetoric" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "legal_corpus", "official_rhetoric": true, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-004", "name": "MapRegion (геолокации)", "owner": "QazLake", "category": "media", "source_type": "download", "formats": [ "JSON" ], "license": "proprietary", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-005", "name": "Echo Sounder (GDELT/NewsData/RSS)", "owner": "QazLake", "category": "media", "source_type": "api", "formats": [ "JSON", "RSS" ], "license": "mixed", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media" ], "consumer_tags": [ "news_corpus" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-006", "name": "OrtCom (пресс-релизы госорганов)", "owner": "QazLake", "category": "media", "source_type": "scrape", "formats": [ "JSON", "HTML" ], "license": "gov-open", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media", "official_rhetoric", "speech_text", "quote_base", "thesis_base", "lang_kk", "lang_ru", "kazakhstan" ], "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_text", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-007", "name": "Total KZ (казахстанские СМИ)", "owner": "QazLake", "category": "media", "source_type": "scrape", "formats": [ "JSON" ], "license": "proprietary", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media" ], "consumer_tags": [ "news_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-008", "name": "NPA Collector — zan.gov.kz (НПА)", "owner": "QazLake", "category": "media", "source_type": "scrape", "formats": [ "JSON", "PDF" ], "license": "gov-open", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "legal" ], "consumer_tags": [ "legal_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "content_kind": "legal_corpus", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-009", "name": "Telegram (казахстанские каналы)", "owner": "QazLake", "category": "media", "source_type": "scrape", "formats": [ "JSON" ], "license": "mixed", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 300, "cache_ttl_s": 3600, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "high", "provenance_required": true }, { "source_id": "media-010", "name": "Tokaev Module (тезисы Президента)", "owner": "QazLake", "category": "media", "source_type": "scrape", "formats": [ "JSON", "PDF" ], "license": "gov-open", "attribution": "QazLake", "priority": "P1", "scope_tags": [ "media", "official_rhetoric", "speech_text", "quote_base", "thesis_base", "lang_kk", "lang_ru", "kazakhstan" ], "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_text", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-011", "name": "YouTube — Qazaqstan TV / Azattyq TV", "owner": "Google / YouTube", "category": "media", "source_type": "api", "formats": [ "JSON", "txt" ], "license": "mixed", "attribution": "Google / YouTube", "priority": "P3", "scope_tags": [ "media" ], "languages": [ "kk" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-012", "name": "Nursultan Nazarbayev Speech Dataset (Kaggle)", "owner": "Kaggle / Bolat Tleubayev", "category": "media", "source_type": "download", "formats": [ "WAV", "JSON" ], "license": "kaggle-terms", "attribution": "Kaggle / Bolat Tleubayev", "priority": "P2", "scope_tags": [ "media", "official_rhetoric", "speech_audio", "lang_kk", "lang_ru", "kazakhstan" ], "consumer_tags": [ "official_rhetoric", "speech_audio", "general_corpus" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_audio", "official_rhetoric": true, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "media-013", "name": "Н.А. Назарбаев — speeches interviews and addresses", "owner": "nazarbayev.kz", "category": "media", "source_type": "scrape", "formats": [ "HTML", "PDF" ], "license": "official-site-review", "attribution": "nazarbayev.kz", "priority": "P2", "scope_tags": [ "media", "official_rhetoric", "speech_text", "quote_base", "thesis_base", "lang_kk", "lang_ru", "kazakhstan" ], "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base", "general_corpus" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_text", "official_rhetoric": true, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "medium", "provenance_required": true }, { "source_id": "nlp-001", "name": "KSC2 — Kazakh Speech Corpus 2", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "WAV", "JSON" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P1", "scope_tags": [ "nlp", "speech_audio", "asr_dataset", "lang_kk", "kazakhstan" ], "consumer_tags": [ "speech_audio", "asr_dataset", "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_audio", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-002", "name": "KazParC — Kazakh Parallel Corpus", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P1", "scope_tags": [ "nlp", "parallel_corpus", "translation", "official_rhetoric", "speech_text", "lang_kk", "lang_en", "lang_ru", "lang_tr", "kazakhstan" ], "consumer_tags": [ "parallel_corpus", "translation", "official_rhetoric", "speech_text", "general_corpus", "quote_base", "thesis_base" ], "languages": [ "kk", "en", "ru", "tr" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "parallel_corpus", "official_rhetoric": true, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-003", "name": "ISSAI KAZ-LLM", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "bin", "safetensors" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P1", "scope_tags": [ "nlp" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-004", "name": "fastText Word Vectors — Kazakh (kk)", "owner": "Meta AI", "category": "nlp", "source_type": "download", "formats": [ "bin" ], "license": "CC-BY-SA", "attribution": "Meta AI", "priority": "P2", "scope_tags": [ "nlp" ], "languages": [ "kk" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-005", "name": "CC-100 — Kazakh (kk)", "owner": "Meta AI / CommonCrawl", "category": "nlp", "source_type": "download", "formats": [ "txt", "gz" ], "license": "open", "attribution": "Meta AI / CommonCrawl", "priority": "P2", "scope_tags": [ "nlp" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-006", "name": "Leipzig Kazakh Web Corpora 2019", "owner": "Uni Leipzig", "category": "nlp", "source_type": "download", "formats": [ "txt", "CSV" ], "license": "CC-BY", "attribution": "Uni Leipzig", "priority": "P2", "scope_tags": [ "nlp" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-007", "name": "KSD — Kazakh Speech Dataset (OpenSLR SLR140)", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "WAV", "JSON" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P3", "scope_tags": [ "nlp", "speech_audio", "asr_dataset", "lang_kk", "kazakhstan" ], "consumer_tags": [ "speech_audio", "asr_dataset", "general_corpus", "speech_synthesis" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_audio", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-008", "name": "KazakhTTS2 — Text-to-Speech Corpus", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "WAV", "JSON" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P3", "scope_tags": [ "nlp", "speech_audio", "speech_synthesis", "lang_kk", "kazakhstan" ], "consumer_tags": [ "speech_audio", "speech_synthesis", "general_corpus", "asr_dataset" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_audio", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-009", "name": "KazNERD — Named Entity Recognition", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P3", "scope_tags": [ "nlp", "ner_dataset", "news_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "ner_dataset", "news_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-010", "name": "KazSAnDRA — Sentiment Analysis Dataset", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P3", "scope_tags": [ "nlp", "sentiment_dataset", "lang_kk", "kazakhstan" ], "consumer_tags": [ "sentiment_dataset", "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "sentiment_dataset", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-011", "name": "Kazakh Instruction v2 (LLaMA fine-tuning)", "owner": "AmanMussa (HF)", "category": "nlp", "source_type": "download", "formats": [ "JSON" ], "license": "open", "attribution": "AmanMussa (HF)", "priority": "P3", "scope_tags": [ "nlp" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-012", "name": "Multidomain Kazakh Dataset", "owner": "kz-transformers (HF)", "category": "nlp", "source_type": "download", "formats": [ "txt", "JSON" ], "license": "open", "attribution": "kz-transformers (HF)", "priority": "P3", "scope_tags": [ "nlp", "general_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-013", "name": "National Corpus of Kazakh", "owner": "КазУниверситет", "category": "nlp", "source_type": "download", "formats": [ "XML", "txt" ], "license": "proprietary", "attribution": "КазУниверситет", "priority": "P3", "scope_tags": [ "nlp", "general_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-014", "name": "NITEC KazLLM", "owner": "NITEC (HF)", "category": "nlp", "source_type": "download", "formats": [ "bin", "safetensors" ], "license": "CC-BY", "attribution": "NITEC (HF)", "priority": "P3", "scope_tags": [ "nlp" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-015", "name": "KazQAD — Kazakh Question Answering Dataset", "owner": "ISSAI NU", "category": "nlp", "source_type": "download", "formats": [ "JSON", "CSV" ], "license": "CC-BY-4.0", "attribution": "ISSAI NU", "priority": "P3", "scope_tags": [ "nlp", "qa_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "qa_corpus", "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "qa_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-016", "name": "Kazakhstani and Russian News Corpus (Mendeley)", "owner": "Mendeley Data", "category": "nlp", "source_type": "download", "formats": [ "CSV", "JSON", "txt" ], "license": "research-review", "attribution": "Mendeley Data", "priority": "P1", "scope_tags": [ "nlp", "news_corpus", "lang_kk", "lang_ru", "kazakhstan", "cis" ], "consumer_tags": [ "news_corpus", "general_corpus" ], "languages": [ "kk", "ru" ], "region": "kazakhstan", "region_tags": [ "kazakhstan", "cis" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-017", "name": "Lenta.Ru News Dataset", "owner": "yutkin", "category": "nlp", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "open", "attribution": "yutkin", "priority": "P2", "scope_tags": [ "nlp", "news_corpus", "lang_ru", "cis" ], "consumer_tags": [ "news_corpus", "general_corpus" ], "languages": [ "ru" ], "region": "cis", "region_tags": [ "cis" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-018", "name": "russian_news_corpus", "owner": "maxoodf", "category": "nlp", "source_type": "download", "formats": [ "txt", "bz2" ], "license": "open", "attribution": "maxoodf", "priority": "P2", "scope_tags": [ "nlp", "news_corpus", "lang_ru", "cis" ], "consumer_tags": [ "news_corpus", "general_corpus" ], "languages": [ "ru" ], "region": "cis", "region_tags": [ "cis" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-019", "name": "Uzbek-Kazakh Parallel Corpus", "owner": "Data in Brief / ScienceDirect", "category": "nlp", "source_type": "download", "formats": [ "CSV", "txt" ], "license": "research-review", "attribution": "Data in Brief / ScienceDirect", "priority": "P2", "scope_tags": [ "nlp", "parallel_corpus", "translation", "lang_kk", "lang_uz", "central_asia" ], "consumer_tags": [ "parallel_corpus", "translation", "general_corpus" ], "languages": [ "kk", "uz" ], "region": "central_asia", "region_tags": [ "central_asia" ], "content_kind": "parallel_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-020", "name": "ISSAI NLP Datasets — Nazarbayev University", "owner": "ISSAI NU / IS2AI", "category": "nlp", "source_type": "api", "formats": [ "JSON", "Markdown", "HTML" ], "license": "mixed", "attribution": "ISSAI NU / IS2AI", "priority": "P2", "scope_tags": [ "nlp", "speech_audio", "ner_dataset", "sentiment_dataset", "qa_corpus", "general_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "speech_audio", "ner_dataset", "sentiment_dataset", "qa_corpus", "general_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "speech_audio", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-021", "name": "QazCorpus — National Corpus of Kazakh Language", "owner": "Институт языкознания им. А. Байтурсынова", "category": "nlp", "source_type": "api", "formats": [ "JSON", "HTML", "txt" ], "license": "mixed", "attribution": "Институт языкознания им. А. Байтурсынова", "priority": "P2", "scope_tags": [ "nlp", "general_corpus", "lang_kk", "kazakhstan" ], "consumer_tags": [ "general_corpus" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-022", "name": "Tajik Web Corpus", "owner": "TajikNLPWorld", "category": "nlp", "source_type": "download", "formats": [ "JSON", "txt" ], "license": "open", "attribution": "TajikNLPWorld", "priority": "P2", "scope_tags": [ "nlp", "general_corpus", "news_corpus", "lang_tg", "central_asia" ], "consumer_tags": [ "general_corpus", "news_corpus" ], "languages": [ "tg" ], "region": "central_asia", "region_tags": [ "central_asia", "global" ], "content_kind": "news_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-023", "name": "Manifesto Corpus / ManifestoBERTa", "owner": "Manifesto Project", "category": "nlp", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "research-review", "attribution": "Manifesto Project", "priority": "P2", "scope_tags": [ "nlp", "political_discourse", "thesis_base", "official_rhetoric", "lang_en", "lang_ru", "global" ], "consumer_tags": [ "political_discourse", "thesis_base", "official_rhetoric", "general_corpus", "quote_base" ], "languages": [ "en", "ru" ], "region": "global", "region_tags": [ "global" ], "content_kind": "political_discourse", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-024", "name": "ParlaMint 5.0", "owner": "CLARIN", "category": "nlp", "source_type": "download", "formats": [ "XML", "TEI", "CoNLL-U", "TSV" ], "license": "CC-BY-4.0", "attribution": "CLARIN", "priority": "P2", "scope_tags": [ "nlp", "parliament_corpus", "official_rhetoric", "quote_base", "thesis_base", "lang_en", "lang_ru", "lang_tr", "global" ], "consumer_tags": [ "parliament_corpus", "official_rhetoric", "quote_base", "thesis_base" ], "languages": [ "en", "ru", "tr" ], "region": "global", "region_tags": [ "global" ], "content_kind": "parliament_corpus", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-025", "name": "ParlaCAP", "owner": "CLARIN.SI / CLASSLA", "category": "nlp", "source_type": "download", "formats": [ "TSV", "JSON" ], "license": "research-review", "attribution": "CLARIN.SI / CLASSLA", "priority": "P2", "scope_tags": [ "nlp", "parliament_corpus", "official_rhetoric", "thesis_base", "political_discourse", "lang_en", "global" ], "consumer_tags": [ "parliament_corpus", "official_rhetoric", "thesis_base", "political_discourse", "general_corpus" ], "languages": [ "en" ], "region": "global", "region_tags": [ "global" ], "content_kind": "parliament_corpus", "official_rhetoric": true, "is_corpus": true, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-026", "name": "Corpus of Political Speeches (HKBU)", "owner": "Hong Kong Baptist University", "category": "nlp", "source_type": "download", "formats": [ "HTML", "txt" ], "license": "research-review", "attribution": "Hong Kong Baptist University", "priority": "P2", "scope_tags": [ "nlp", "official_rhetoric", "speech_text", "quote_base", "thesis_base", "political_discourse", "lang_en", "lang_zh", "global" ], "consumer_tags": [ "official_rhetoric", "speech_text", "quote_base", "thesis_base", "political_discourse", "general_corpus" ], "languages": [ "en", "zh" ], "region": "global", "region_tags": [ "global" ], "content_kind": "speech_text", "official_rhetoric": true, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-027", "name": "UzbekPOS — Multi-domain POS Dataset", "owner": "Mendeley Data", "category": "nlp", "source_type": "download", "formats": [ "CSV", "JSON" ], "license": "research-review", "attribution": "Mendeley Data", "priority": "P2", "scope_tags": [ "nlp", "pos_dataset", "lang_uz", "central_asia" ], "consumer_tags": [ "pos_dataset", "general_corpus" ], "languages": [ "uz" ], "region": "central_asia", "region_tags": [ "central_asia" ], "content_kind": "pos_dataset", "official_rhetoric": false, "is_corpus": true, "public_allowed": "review", "redistribution_allowed": "review", "pii_risk": "low", "provenance_required": true }, { "source_id": "nlp-028", "name": "Uzbek-Corpus-Sample", "owner": "elmurod1202", "category": "nlp", "source_type": "download", "formats": [ "txt", "JSON" ], "license": "open", "attribution": "elmurod1202", "priority": "P3", "scope_tags": [ "nlp", "general_corpus", "lang_uz", "central_asia" ], "consumer_tags": [ "general_corpus" ], "languages": [ "uz" ], "region": "central_asia", "region_tags": [ "central_asia" ], "content_kind": "general_corpus", "official_rhetoric": false, "is_corpus": true, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-001", "name": "JRC Global Surface Water", "owner": "JRC", "category": "satellite", "source_type": "gee", "formats": [ "GeoTIFF", "NetCDF" ], "license": "CC-BY", "attribution": "JRC", "priority": "P1", "scope_tags": [ "lakes", "hydro" ], "region": "global", "region_tags": [ "global" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 31536000, "cache_ttl_s": 63072000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-002", "name": "Google Earth Engine", "owner": "Google / NASA", "category": "satellite", "source_type": "gee", "formats": [ "Python/JS API", "GeoTIFF", "NetCDF" ], "license": "open", "attribution": "Google / NASA", "priority": "P1", "scope_tags": [ "lakes", "hydro", "climate", "geo", "environment" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-003", "name": "Copernicus DEM GLO-30", "owner": "ESA", "category": "satellite", "source_type": "download", "formats": [ "GeoTIFF" ], "license": "open", "attribution": "ESA", "priority": "P1", "scope_tags": [ "geo", "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-004", "name": "Sentinel-2 MSI", "owner": "ESA", "category": "satellite", "source_type": "gee", "formats": [ "GeoTIFF", "JPEG2000" ], "license": "open", "attribution": "ESA", "priority": "P1", "scope_tags": [ "lakes", "environment", "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-005", "name": "DAHITI — Database for Hydrological Time Series", "owner": "TU München", "category": "satellite", "source_type": "api", "formats": [ "CSV", "NetCDF", "JSON" ], "license": "CC-BY", "attribution": "TU München", "priority": "P2", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-006", "name": "ICESat-2 NASA ATLAS", "owner": "NASA", "category": "satellite", "source_type": "api", "formats": [ "HDF5", "CSV" ], "license": "open", "attribution": "NASA", "priority": "P2", "scope_tags": [ "hydro", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-007", "name": "NASA Earthdata (MODIS/GRACE/SRTM)", "owner": "NASA", "category": "satellite", "source_type": "api", "formats": [ "HDF", "NetCDF", "GeoTIFF" ], "license": "open", "attribution": "NASA", "priority": "P3", "scope_tags": [ "hydro", "climate", "geo", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-008", "name": "Copernicus Data Space Ecosystem", "owner": "ESA", "category": "satellite", "source_type": "api", "formats": [ "GeoTIFF", "JPEG2000", "NetCDF" ], "license": "open", "attribution": "ESA", "priority": "P3", "scope_tags": [ "satellite", "geo", "environment", "lakes" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "satellite-009", "name": "Sentinel-5P (атмосфера)", "owner": "ESA", "category": "satellite", "source_type": "gee", "formats": [ "NetCDF", "HDF5" ], "license": "open", "attribution": "ESA", "priority": "P3", "scope_tags": [ "environment", "climate" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "seis-001", "name": "KZNET — FDSN сейсмологическая сеть КЗ", "owner": "ИНИС МОН РК", "category": "seismology", "source_type": "download", "formats": [ "miniseed", "XML" ], "license": "open", "attribution": "ИНИС МОН РК", "priority": "P3", "scope_tags": [ "seismology" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 300, "cache_ttl_s": 3600, "public_allowed": "yes", "redistribution_allowed": "yes", "pii_risk": "low", "provenance_required": true }, { "source_id": "seis-002", "name": "KNDC — Казахстанский сейсмологический центр", "owner": "МОН РК", "category": "seismology", "source_type": "download", "formats": [ "CSV", "XML" ], "license": "gov-open", "attribution": "МОН РК", "priority": "P3", "scope_tags": [ "seismology", "hydro" ], "languages": [ "kk" ], "region": "kazakhstan", "region_tags": [ "kazakhstan" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 86400, "cache_ttl_s": 172800, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "stat-001", "name": "Бюро национальной статистики stat.gov.kz", "owner": "БНС РК", "category": "statistics", "source_type": "download", "formats": [ "CSV", "XLSX", "JSON" ], "license": "gov-open", "attribution": "БНС РК", "priority": "P1", "scope_tags": [ "socioeconomic", "environment", "hydro" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true }, { "source_id": "stat-002", "name": "Региональная статистика stat.gov.kz", "owner": "БНС РК", "category": "statistics", "source_type": "download", "formats": [ "XLSX", "CSV", "JSON" ], "license": "gov-open", "attribution": "БНС РК", "priority": "P3", "scope_tags": [ "socioeconomic", "geo" ], "official_rhetoric": false, "is_corpus": false, "refresh_cadence_s": 2592000, "cache_ttl_s": 5184000, "public_allowed": "yes", "redistribution_allowed": "attribution", "pii_risk": "low", "provenance_required": true } ], "operations": { "status": "available", "observed_at": "2026-07-18T18:23:21Z", "hours": 24, "endpoint": "https://lake.qdev.run/api/v1/data-platform/runs?limit=100", "summary": { "runs": 100, "success": 100, "error": 0, "timeout": 0, "partial": 0, "running": 0, "last_started_at": "2026-07-18T18:23:03+00:00" }, "runs": [ { "id": "qazpipe:collector_nlp_sync:1784398983:4103869", "collector_name": "collector_nlp_sync", "source_id": "collector_nlp_sync", "status": "success", "started_at": "2026-07-18T18:23:03+00:00", "finished_at": "2026-07-18T18:23:10+00:00", "duration_sec": 7, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_article_fetcher:1784398923:4092783", "collector_name": "collector_article_fetcher", "source_id": "collector_article_fetcher", "status": "success", "started_at": "2026-07-18T18:22:03+00:00", "finished_at": "2026-07-18T18:22:13+00:00", "duration_sec": 10, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_blogs_sync:1784398743:4066466", "collector_name": "collector_blogs_sync", "source_id": "collector_blogs_sync", "status": "success", "started_at": "2026-07-18T18:19:03+00:00", "finished_at": "2026-07-18T18:19:04+00:00", "duration_sec": 1, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qalam:analysis:177002f0-9a05-45db-a89a-8a13a99f87ed", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T18:17:40.593000+00:00", "finished_at": "2026-07-18T18:17:40.593000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 }, { "id": "qazpipe:collector_shadow_bridge:1784398623:4045172", "collector_name": "collector_shadow_bridge", "source_id": "collector_shadow_bridge", "status": "success", "started_at": "2026-07-18T18:17:03+00:00", "finished_at": "2026-07-18T18:17:24+00:00", "duration_sec": 21, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:qazlake_to_echo_sync:1784398504:4022775", "collector_name": "qazlake_to_echo_sync", "source_id": "qazlake_to_echo_sync", "status": "success", "started_at": "2026-07-18T18:15:04+00:00", "finished_at": "2026-07-18T18:15:06+00:00", "duration_sec": 2, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_kz_media:1784398324:3992774", "collector_name": "collector_kz_media", "source_id": "collector_kz_media", "status": "success", "started_at": "2026-07-18T18:12:04+00:00", "finished_at": "2026-07-18T18:12:07+00:00", "duration_sec": 3, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_youtube:1784398324:3992776", "collector_name": "collector_youtube", "source_id": "collector_youtube", "status": "success", "started_at": "2026-07-18T18:12:04+00:00", "finished_at": "2026-07-18T18:14:34+00:00", "duration_sec": 150, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:kz_media_collector:1784398204:3971281", "collector_name": "kz_media_collector", "source_id": "kz_media_collector", "status": "success", "started_at": "2026-07-18T18:10:04+00:00", "finished_at": "2026-07-18T18:18:44+00:00", "duration_sec": 520, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_kz_media:1784397904:3919365", "collector_name": "collector_kz_media", "source_id": "collector_kz_media", "status": "success", "started_at": "2026-07-18T18:05:04+00:00", "finished_at": "2026-07-18T18:09:06+00:00", "duration_sec": 242, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_smi:1784397783:3897696", "collector_name": "collector_smi", "source_id": "collector_smi", "status": "success", "started_at": "2026-07-18T18:03:03+00:00", "finished_at": "2026-07-18T18:03:50+00:00", "duration_sec": 47, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qalam:analysis:7484b301-3748-4891-8f9d-d70f6db0ba09", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T18:02:40.469000+00:00", "finished_at": "2026-07-18T18:02:40.469000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 }, { "id": "qalam:analysis:dc5b0008-c389-4d20-8a09-c47ef191eee5", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T18:00:53.175000+00:00", "finished_at": "2026-07-18T18:00:53.175000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 }, { "id": "qalam:analysis:4a540142-5e5a-4a4a-bc2c-5a3140483a79", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T17:58:40.196000+00:00", "finished_at": "2026-07-18T17:58:40.196000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 }, { "id": "qazpipe:collector_youtube_sync:1784397423:3839370", "collector_name": "collector_youtube_sync", "source_id": "collector_youtube_sync", "status": "success", "started_at": "2026-07-18T17:57:03+00:00", "finished_at": "2026-07-18T17:57:06+00:00", "duration_sec": 3, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_threads:1784397389:3834028", "collector_name": "collector_threads", "source_id": "collector_threads", "status": "success", "started_at": "2026-07-18T17:56:29+00:00", "finished_at": "2026-07-18T17:58:22+00:00", "duration_sec": 113, "items_fetched": 8, "items_new": 6, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_mastodon:1784397206:3801001", "collector_name": "collector_mastodon", "source_id": "collector_mastodon", "status": "success", "started_at": "2026-07-18T17:53:26+00:00", "finished_at": "2026-07-18T17:53:46+00:00", "duration_sec": 20, "items_fetched": 120, "items_new": 61, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_nlp_sync:1784397183:3797052", "collector_name": "collector_nlp_sync", "source_id": "collector_nlp_sync", "status": "success", "started_at": "2026-07-18T17:53:03+00:00", "finished_at": "2026-07-18T17:53:10+00:00", "duration_sec": 7, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_threads:1784397178:3796292", "collector_name": "collector_threads", "source_id": "collector_threads", "status": "success", "started_at": "2026-07-18T17:52:58+00:00", "finished_at": "2026-07-18T17:53:15+00:00", "duration_sec": 17, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_blogs_sync:1784396944:3758104", "collector_name": "collector_blogs_sync", "source_id": "collector_blogs_sync", "status": "success", "started_at": "2026-07-18T17:49:04+00:00", "finished_at": "2026-07-18T17:49:05+00:00", "duration_sec": 1, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_telegram:1784396763:3729660", "collector_name": "collector_telegram", "source_id": "collector_telegram", "status": "success", "started_at": "2026-07-18T17:46:03+00:00", "finished_at": "2026-07-18T17:48:13+00:00", "duration_sec": 130, "items_fetched": 0, "items_new": 0, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qazpipe:collector_bluesky:1784396726:3723734", "collector_name": "collector_bluesky", "source_id": "collector_bluesky", "status": "success", "started_at": "2026-07-18T17:45:26+00:00", "finished_at": "2026-07-18T17:45:50+00:00", "duration_sec": 24, "items_fetched": 198, "items_new": 64, "items_duplicate": 0, "items_error": 0, "trigger": "cron" }, { "id": "qalam:analysis:05aac885-6eea-40bf-b20a-58feaf952f4f", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T17:43:39.647000+00:00", "finished_at": "2026-07-18T17:43:39.647000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 }, { "id": "qalam:analysis:eb6a1804-f8e3-4720-96f3-035aa5d1d20f", "collector_name": "qalam_text_analysis", "source_id": "qalam", "status": "success", "started_at": "2026-07-18T17:36:55.074000+00:00", "finished_at": "2026-07-18T17:36:55.074000+00:00", "items_fetched": 1, "items_new": 1, "items_duplicate": 0, "items_error": 0 } ] } }