{"block_signal_type_counts":{"block":661431,"dns-blocking":34373,"http-blocking-blockpage":1,"http-blocking-tcp-reset":3544,"http-blocking-timeout":1429,"interference":1131},"block_signals":["dns-blocking","http-blocking-tcp-reset","http-blocking-timeout","http-blocking-blockpage","block","blocking","interference","tcp-reset","blockpage","tor-blocking","header-manipulation","middlebox-detection"],"caveats":["This is a RECOMMENDATION. It is not wired into probe_module.py or the live probe scheduler \u2014 nothing changes the probe cadence yet. It produces a priority list a scheduler or human can choose to consume.","Thompson sampling here treats each (country, domain) pair as an INDEPENDENT bandit arm. In reality DPI policy correlates domains within a country and censors flip many sites at once \u2014 a hierarchical / contextual model would be more correct. Treat the ranking as a heuristic.","A high-variance pair may just be intermittently REACHABLE (flaky resolver, congested transit) rather than censorship-uncertain. The recent-flip term partly separates genuinely-contested pairs from merely-noisy ones, but not perfectly.","Cold pairs with fewer than 2 observations are not ranked here; the existing fixed-list scheduler already covers them.","Recency weighting uses a 45-day half-life, so a block state that flipped months ago is heavily discounted relative to fresh observations."],"endpoints":["/v1/atlas/probe-priority","/v1/atlas/probe-priority/info"],"generated_at":"2026-11-19T04:50:01.548406+00:00","halflife_days":45.0,"is_recommendation_only":true,"mean_posterior_variance":0.028914,"method":"Thompson sampling per (country, domain) bandit arm","min_observations":2,"prior":{"alpha":0.5,"beta":0.5,"name":"Jeffreys Beta(0.5, 0.5)"},"priority_formula":"posterior_variance * recency_weight * flip_weight * (1 + thompson_weight * (1 - |sample-0.5|*2))","random_seed":20260521,"schema":"voidly-atlas-probe-scheduling-priority/v1","summary":"Each (country, domain) pair carries a Beta(alpha, beta) posterior over P(blocked). alpha/beta accumulate recency-weighted block / unblock observations from the evidence table. The posterior variance is the information-gain proxy: a fresh probe is worth most where the posterior is widest. A Thompson draw from each Beta adds bandit exploration. Pairs are ranked by variance * recency * recent-flip * Thompson term. The output is a RECOMMENDED priority list \u2014 it is not wired into the live probe scheduler.","thompson_weight":0.5,"top_k_country_counts":{"AE":3,"AF":5,"AU":8,"AZ":2,"BD":3,"BH":2,"BO":1,"BR":10,"BY":15,"CA":3,"CN":4,"CU":5,"DE":3,"EG":3,"ES":3,"FI":1,"FR":9,"GB":5,"ID":3,"IN":12,"IQ":3,"IR":2,"JO":4,"JP":22,"KH":3,"KR":8,"KW":3,"KZ":3,"LA":5,"MA":3,"MM":1,"MN":5,"MX":4,"MY":3,"NG":1,"NI":1,"NL":37,"PK":3,"QA":3,"RO":14,"RU":3,"RW":1,"SA":3,"SD":3,"SE":1,"SG":20,"SY":5,"TH":3,"TR":4,"TZ":1,"UG":2,"US":9,"VE":4,"VN":3,"ZA":10},"total_evidence_rows_scanned":871773,"total_pairs_cold_skipped":1015,"total_pairs_scored":5111,"total_pairs_with_recent_flip":261,"unblock_signals":["ok"],"window_days":365,"wired_into_scheduler":false}
