sodermalm · page built 2026-09-28 03:50 UTC

Coverage, last 60 runs

Forecast mode. The dashed line is the 80 % the interval claims; below it the published band is too narrow.

Last night

LAST NIGHT  ·  sodermalm  ·  2026-09-26
=======================================

  READINGS   INCOMPLETE - review this night before trusting it

      21 streets reported in the 7 nights before; tonight 0 complete,
      10 partial, 11 missing.

      MISSING (no reading tonight)
        street                   class       hours  hours with no reading  previous reading sensor (edge_id)
        Centralbron              trunk           0  all                    2026-09-24       1278202819285001502
        Centralbron              trunk           0  all                    2026-09-24       8782737897325117851
        Johanneshovsbron         trunk           0  all                    2026-09-24       1131825193555294041
        Johanneshovsbron         trunk           0  all                    2026-09-24       2285120602095304578
        Riddarfjärdsavfarten     trunk_link      0  all                    2026-09-24       6273664228741062648
        Riddarfjärdsavfarten     trunk_link      0  all                    2026-09-24       8449147494588363671
        Söderledstunneln         trunk           0  all                    2026-09-24       2121158910487139834
        Söderledstunneln         trunk           0  all                    2026-09-24       4608176295624378895
        Söderledstunneln         tertiary        0  all                    2026-09-24       6049545849702297001
        Söderledstunneln         trunk           0  all                    2026-09-24       6141289010017751098
        Söderledstunneln         trunk           0  all                    2026-09-24       7287665418073636328

      PARTIAL (some hours)
        street                   class       hours  hours with no reading  previous reading sensor (edge_id)
        Johanneshovsbron         trunk           1  01-23                  2026-09-26       3010561369796539871
        Riddarfjärdsavfarten     trunk_link      1  01-23                  2026-09-26       2293438315898261338
        Riddarfjärdspåfarten     trunk_link      1  01-23                  2026-09-26       6596515135589978132
        Skansbroavfarten         trunk_link      1  01-23                  2026-09-26       5963811513103536080
        Skansbropåfarten         trunk_link      1  01-23                  2026-09-26       8107401693088942229
        Söderledstunneln         tertiary        1  01-23                  2026-09-26       733914796050831227
        Söderledstunneln         trunk           1  01-23                  2026-09-26       2265962745694732676
        Söderledstunneln         trunk           1  01-23                  2026-09-26       2571250825381427901
        Söderledstunneln         trunk           1  01-23                  2026-09-26       2612359577996334200
        Södermalmsavfarten       tertiary        1  01-23                  2026-09-26       6012602496528382344

      NOTE: 2026-09-27 absorbed no counts, so it has no day factor. The figures
      below are for 2026-09-26, the last night that did.


  STATUS   ok

      10 streets reported.

      the network ran          +35.8%  against a normal night
      the calendar expected     +7.0%  from holidays and season
      so unexplained           +26.9%

      27% above what the calendar predicts.

      change scores, one pair for the WHOLE network - never one street:
        up     0.47 / 10  
        down   0.00 / 10  

      No alarm. 9.5 to go.


  THE STREETS THAT REPORTED
  ------------------------

  street                    vs normal  calendar  network      own      up  down  status
  Skansbroavfarten             +40.3%     +7.0%   +56.8%   -16.4%    0.00  0.00  ok
  Skansbropåfarten             +37.0%     +7.0%   +37.3%    -6.8%    0.00  0.00  ok
  Riddarfjärdspåfarten         +65.0%     +7.0%   +60.4%    -3.8%    0.00  0.00  ok
  Riddarfjärdsavfarten         +43.7%     +7.0%   +36.9%    -1.9%    0.00  0.00  ok
  Söderledstunneln             +40.0%     +7.0%   +29.1%    +1.3%    0.00  0.00  ok
  Söderledstunneln             +52.9%     +7.0%   +40.3%    +1.8%    0.00  0.00  ok
  Söderledstunneln             +39.2%     +7.0%   +26.9%    +2.5%    0.00  0.00  ok
  Söderledstunneln             +39.5%     +7.0%   +26.3%    +3.2%    0.00  0.00  ok
  Johanneshovsbron             +55.4%     +7.0%   +34.8%    +7.7%    0.00  0.00  ok
  Södermalmsavfarten           +49.7%     +7.0%   +18.4%   +18.1%    0.43  0.00  ok

  'own' is what the street did beyond the calendar and beyond the whole network's night;
  the two totals accumulate it. One pair per street, not one for the city.

Honesty statement

HONESTY STATEMENT  ·  sodermalm  ·  as of 2026-09-27
====================================================

Of the times we published an 80 % interval, how often did the truth fall inside it?

  STREETS WE MEASURE

      estimate mode    80.4%   honest
                      median error 0.097 log  (x1.10)
      forecast mode    69.2%   TOO NARROW by 11 points
                      median error 0.176 log  (x1.19)
      over 5,202 nights.  The gap between the two modes is what knowing the day
      is worth, measured rather than asserted.

      Lately, on the same streets, cell-weighted the same way:

        window          estimate  forecast   nights    cells
        all time           80.4%     69.2%    5,202        -
        last 365 days      91.7%     85.1%      186   63,627
        last 90 days       93.5%     84.2%       90   43,510

      CALENDAR days, not the last N scored nights: the sensor fleet thinned, so
      the last 365 SCORED nights span over three calendar years here and would
      be a misleading thing to call 'the last year'. A window with few nights is
      a weak signal, which is why the counts are beside the figures.

  STREETS WE DO NOT

      *** THIS NUMBER IS FROM AN OLDER RUN. validation_edges.parquet predates
          the model beside it, so the two describe different fits. Re-run with
          validation enabled - `pipeline <area> --until <date> --kfold` - before
          quoting it. ***
      coverage         65.6%   TOO NARROW by 14 points
                      median error 0.586 log  (x1.80)
      over 15 streets whose counts were hidden and then predicted exactly
      as an unmeasured street is. This is the claim the product rests on.

      Worst-covered, which the pooled figure hides:

        6596515135589978132   coverage 11.4%   error x4.21   (2266 cells)
        2735134620436969359   coverage 28.1%   error x5.70   (263 cells)
        3551390319739141482   coverage 51.6%   error x3.72   (128 cells)
        9123579490307474467   coverage 54.9%   error x2.83   (627 cells)
        3918353604589034303   coverage 70.7%   error x3.25   (167 cells)

      A pooled number blends a well-calibrated majority with a few streets that
      are confidently wrong. Both are worth reporting; only one is a tuning
      problem.


HOW MUCH IS REPORTING
---------------------

      21 streets report on a typical recent night (at or above the 5 the day factor needs).

  HOW MUCH OF THE NETWORK IS MEASURED AT ALL

      1,109 of 4,564 streets (24.3 %) have ever been counted.
      The other 3,455 are inferred from the network. A city where
      3 % of streets carry recent measurement is a different product from one where
      30 % do, and a uniform-looking map should not imply uniform confidence.

      Of the 1,109 counted, 43 were counted within 120 days and
      carry the narrow measured-street band. The remaining 1,066 are STALE -
      counted once, long ago - and are banded as inferred streets, because that
      is what they now are. Their level comes from the drift and their neighbours,
      not from their own sensor.

Change alerts

CHANGE ALERTS  ·  sodermalm  ·  as of 2026-09-27
================================================

7 confirmed changes. A change is reported when the network's day factor stays displaced for a run of dates, not when a single day looks unusual.

  2010-03-10  UP     +33.2%
      began        2010-03-10   (when the shift started, not when it was noticed)
      confirmed    2010-05-05   (105 processed dates in the run)
      size         +33.2%  (+0.287 log)   peak statistic 10.0

  2010-08-19  UP     +66.0%
      began        2010-08-19   (when the shift started, not when it was noticed)
      confirmed    2010-10-14   (113 processed dates in the run)
      size         +66.0%  (+0.507 log)   peak statistic 11.4

  2012-05-24  UP     +30.8%
      began        2012-05-24   (when the shift started, not when it was noticed)
      confirmed    2012-06-16   (27 processed dates in the run)
      size         +30.8%  (+0.268 log)   peak statistic 10.2

  2013-11-28  UP     +31.5%
      began        2013-11-28   (when the shift started, not when it was noticed)
      confirmed    2013-12-21   (24 processed dates in the run)
      size         +31.5%  (+0.274 log)   peak statistic 10.1

  2020-03-15  DOWN   -20.3%
      began        2020-03-15   (when the shift started, not when it was noticed)
      confirmed    2020-04-01   (75 processed dates in the run)
      size         -20.3%  (-0.227 log)   peak statistic 11.1

  2021-08-12  UP     +24.9%
      began        2021-08-12   (when the shift started, not when it was noticed)
      confirmed    2021-09-04   (25 processed dates in the run)
      size         +24.9%  (+0.222 log)   peak statistic 11.0

  2022-05-05  UP     +23.9%
      began        2022-05-05   (when the shift started, not when it was noticed)
      confirmed    2022-06-12   (39 processed dates in the run)
      size         +23.9%  (+0.215 log)   peak statistic 10.1

What this does NOT tell you:

  · which streets. This watches the whole network's day factor, so it catches a shift
    that moved everything. A single street changing is a different test (paper §8.3).
  · why. Weather, roadworks, a new bridge and a policy change look identical here.
  · that the model has corrected for it. A confirmed change should trigger a local reset;
    until it does, forecasts for the affected streets stay wrong while every daily output
    continues to look right (paper §8).

Each day: what the sensors said, and what the model published

Predicted flow across the whole network, hour by hour.

The model behind these numbers

Recent runs