Skip to content

Commit fd5753a

Browse files
sdspiegclaude
sdspieg
and
claude
committed
Refresh dataset_freshness.json — VIINA events + control caught up
After tonight's stale-dataset triage: - VIINA events: fixed (updater URL patched: master->main + media.githubusercontent.com LFS endpoint). +19,596 rows for 2026, latest 2026-05-27. - VIINA control: new updater built, bulk-loaded 4.37M rows for 2026, latest 2026-05-27 (was Feb 28). Registered for daily 09:00 UTC cron. See Datasets/DATASET_UPDATE_SCHEDULE.md "Stale-dataset triage" section for the full root-cause writeup. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
1 parent 321b030 commit fd5753a

1 file changed

Lines changed: 32 additions & 32 deletions

File tree

‎public/data/dataset_freshness.json‎

Lines changed: 32 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
11
{
2-
"as_of_utc": "2026-05-28T21:48:52Z",
2+
"as_of_utc": "2026-05-29T02:09:33Z",
33
"totals": {
4-
"fresh": 15,
5-
"very_stale": 5,
4+
"fresh": 16,
5+
"very_stale": 4,
66
"lagging": 4,
77
"manual": 1,
88
"stale": 1
@@ -16,7 +16,7 @@
1616
"rows": 1554,
1717
"expected_cadence": "daily",
1818
"expected_max_lag_days": 2,
19-
"days_behind": 0,
19+
"days_behind": 1,
2020
"status": "fresh",
2121
"note": "GitHub JSON refresh; truncate+insert"
2222
},
@@ -28,7 +28,7 @@
2828
"rows": 1554,
2929
"expected_cadence": "daily",
3030
"expected_max_lag_days": 2,
31-
"days_behind": 0,
31+
"days_behind": 1,
3232
"status": "fresh",
3333
"note": "GitHub JSON refresh; truncate+insert"
3434
},
@@ -40,7 +40,7 @@
4040
"rows": 327512,
4141
"expected_cadence": "daily",
4242
"expected_max_lag_days": 400,
43-
"days_behind": 365,
43+
"days_behind": 366,
4444
"status": "fresh",
4545
"note": "Free tier: 12-month rolling window \u2014 ~1y stale is expected"
4646
},
@@ -52,20 +52,20 @@
5252
"rows": 569390,
5353
"expected_cadence": "daily",
5454
"expected_max_lag_days": 2,
55-
"days_behind": 1,
55+
"days_behind": 2,
5656
"status": "fresh",
5757
"note": "GitHub ZIP refresh"
5858
},
5959
{
6060
"dataset": "VIINA control",
6161
"schema_table": "conflict_events.viina_control",
6262
"category": "conflict_events",
63-
"latest_date": "2026-02-28",
64-
"rows": 48617847,
63+
"latest_date": "2026-05-27",
64+
"rows": 51031956,
6565
"expected_cadence": "daily",
6666
"expected_max_lag_days": 7,
67-
"days_behind": 89,
68-
"status": "very_stale",
67+
"days_behind": 2,
68+
"status": "fresh",
6969
"note": "Daily territorial control snapshots"
7070
},
7171
{
@@ -76,7 +76,7 @@
7676
"rows": 2548641,
7777
"expected_cadence": "daily",
7878
"expected_max_lag_days": 14,
79-
"days_behind": 470,
79+
"days_behind": 471,
8080
"status": "very_stale",
8181
"note": "Stale >15mo as of 2026-05 \u2014 needs investigation"
8282
},
@@ -88,7 +88,7 @@
8888
"rows": 2514,
8989
"expected_cadence": "monthly",
9090
"expected_max_lag_days": 60,
91-
"days_behind": 323,
91+
"days_behind": 324,
9292
"status": "very_stale",
9393
"note": "Bellingcat civilian-harm dataset"
9494
},
@@ -100,7 +100,7 @@
100100
"rows": 3728,
101101
"expected_cadence": "daily",
102102
"expected_max_lag_days": 7,
103-
"days_behind": 4,
103+
"days_behind": 5,
104104
"status": "fresh",
105105
"note": "Kaggle-backed; truncate+insert"
106106
},
@@ -112,7 +112,7 @@
112112
"rows": 362470,
113113
"expected_cadence": "daily",
114114
"expected_max_lag_days": 2,
115-
"days_behind": 1,
115+
"days_behind": 2,
116116
"status": "fresh",
117117
"note": "GDELT publishes T-1 daily"
118118
},
@@ -124,7 +124,7 @@
124124
"rows": 383345,
125125
"expected_cadence": "daily",
126126
"expected_max_lag_days": 2,
127-
"days_behind": 1,
127+
"days_behind": 2,
128128
"status": "fresh",
129129
"note": "GKG quotations corpus (coercion subset)"
130130
},
@@ -136,7 +136,7 @@
136136
"rows": 9511,
137137
"expected_cadence": "daily",
138138
"expected_max_lag_days": 2,
139-
"days_behind": 1,
139+
"days_behind": 2,
140140
"status": "fresh",
141141
"note": "GKG quotations corpus (red-line subset)"
142142
},
@@ -148,7 +148,7 @@
148148
"rows": 229,
149149
"expected_cadence": "weekly",
150150
"expected_max_lag_days": 8,
151-
"days_behind": 3,
151+
"days_behind": 4,
152152
"status": "fresh",
153153
"note": "Recomputed Monday 08:00 UTC from coercive quotes"
154154
},
@@ -160,7 +160,7 @@
160160
"rows": 12170,
161161
"expected_cadence": "daily",
162162
"expected_max_lag_days": 7,
163-
"days_behind": 1,
163+
"days_behind": 2,
164164
"status": "fresh",
165165
"note": "CREA incremental API"
166166
},
@@ -172,7 +172,7 @@
172172
"rows": 5239,
173173
"expected_cadence": "quarterly",
174174
"expected_max_lag_days": 120,
175-
"days_behind": 209,
175+
"days_behind": 210,
176176
"status": "lagging",
177177
"note": "Kiel publishes quarterly"
178178
},
@@ -184,7 +184,7 @@
184184
"rows": 1891,
185185
"expected_cadence": "manual",
186186
"expected_max_lag_days": null,
187-
"days_behind": 113,
187+
"days_behind": 114,
188188
"status": "manual",
189189
"note": "Cloudflare blocks VPS \u2014 must be refreshed manually"
190190
},
@@ -196,7 +196,7 @@
196196
"rows": 69818,
197197
"expected_cadence": "daily",
198198
"expected_max_lag_days": 30,
199-
"days_behind": 123,
199+
"days_behind": 124,
200200
"status": "stale",
201201
"note": "Sanctions targets list"
202202
},
@@ -208,7 +208,7 @@
208208
"rows": 8329,
209209
"expected_cadence": "annual",
210210
"expected_max_lag_days": 540,
211-
"days_behind": 513,
211+
"days_behind": 514,
212212
"status": "fresh",
213213
"note": "Annual release ~April each year"
214214
},
@@ -220,7 +220,7 @@
220220
"rows": 1492,
221221
"expected_cadence": "annual",
222222
"expected_max_lag_days": 540,
223-
"days_behind": 513,
223+
"days_behind": 514,
224224
"status": "fresh",
225225
"note": "Annual release"
226226
},
@@ -232,7 +232,7 @@
232232
"rows": 1170,
233233
"expected_cadence": "monthly",
234234
"expected_max_lag_days": 60,
235-
"days_behind": 117,
235+
"days_behind": 118,
236236
"status": "lagging",
237237
"note": "HAPI internally-displaced persons"
238238
},
@@ -244,7 +244,7 @@
244244
"rows": 45890,
245245
"expected_cadence": "monthly",
246246
"expected_max_lag_days": 90,
247-
"days_behind": 513,
247+
"days_behind": 514,
248248
"status": "very_stale",
249249
"note": "HAPI refugees outflow"
250250
},
@@ -256,7 +256,7 @@
256256
"rows": 40866,
257257
"expected_cadence": "monthly",
258258
"expected_max_lag_days": 60,
259-
"days_behind": 89,
259+
"days_behind": 90,
260260
"status": "lagging",
261261
"note": "HAPI conflict events"
262262
},
@@ -268,7 +268,7 @@
268268
"rows": 2945,
269269
"expected_cadence": "annual",
270270
"expected_max_lag_days": 540,
271-
"days_behind": 148,
271+
"days_behind": 149,
272272
"status": "fresh",
273273
"note": "Annual UNHCR release"
274274
},
@@ -280,7 +280,7 @@
280280
"rows": 71,
281281
"expected_cadence": "monthly",
282282
"expected_max_lag_days": 60,
283-
"days_behind": 1730,
283+
"days_behind": 1731,
284284
"status": "very_stale",
285285
"note": "Known long-broken \u2014 has not updated since 2021"
286286
},
@@ -292,7 +292,7 @@
292292
"rows": 596,
293293
"expected_cadence": "monthly",
294294
"expected_max_lag_days": 60,
295-
"days_behind": 88,
295+
"days_behind": 89,
296296
"status": "lagging",
297297
"note": "DeepState UA polygons"
298298
},
@@ -304,7 +304,7 @@
304304
"rows": 2004,
305305
"expected_cadence": "daily",
306306
"expected_max_lag_days": 7,
307-
"days_behind": 1,
307+
"days_behind": 2,
308308
"status": "fresh",
309309
"note": "Confirmed RRLS statements (matview)"
310310
},
@@ -316,7 +316,7 @@
316316
"rows": 364,
317317
"expected_cadence": "daily",
318318
"expected_max_lag_days": 7,
319-
"days_behind": 4,
319+
"days_behind": 5,
320320
"status": "fresh",
321321
"note": "Confirmed NTS statements (matview)"
322322
}

0 commit comments

Comments
 (0)