What the score has and has not shown

Aug 24, 2026: 9 cohort rows were withdrawn after instrument eligibility changed under methodology 2.4, 9 of which had already resolved (Middle range 9). The original registry rows remain recorded. Decision record

Aug 24, 2026: 973 cohort rows were withdrawn after instrument eligibility changed under methodology 2.13, 77 of which had already resolved (Lowest range 2, Middle range 15, Upper range 53, Lower range 7). The original registry rows remain recorded. Decision record

Aug 24, 2026: 148 cohort rows were withdrawn after instrument eligibility changed under methodology 2.14, none of which had resolved. The original registry rows remain recorded. Decision record

Aug 25, 2026: 1,189 cohort rows were withdrawn after instrument eligibility changed under methodology 2.13, 228 of which had already resolved (Lowest range 10, Middle range 122, Upper range 45, Lower range 51). The original registry rows remain recorded. Decision record

Aug 25, 2026: 289 cohort rows were withdrawn after instrument eligibility changed under methodology 2.14, none of which had resolved. The original registry rows remain recorded. Decision record

Aug 29, 2026: 6 cohort rows were withdrawn after instrument eligibility changed under methodology 2.4, none of which had resolved. The original registry rows remain recorded. Decision record

Sep 2, 2026: 21 cohort rows were withdrawn after instrument eligibility changed under methodology 2.14, none of which had resolved. The original registry rows remain recorded. Decision record

Sep 11, 2026: 8 cohort rows were withdrawn after instrument eligibility changed under methodology 2.14, none of which had resolved. The original registry rows remain recorded. Decision record

Sep 7, 2026: Every mean forward return published on this page was overstated, and the largest ones were overstated by a multiple. The cause: a small number of rows whose forward window spans a split or reverse split the price series was never adjusted for. HCWC closed at $0.2352 on 2026-08-28 and at $7.53 on 2026-09-01, a single-session factor of 32.02, and then traded $7.12, $6.99, $7.00. That is a change in share count, not a 4,598% return. Nobody held a position that multiplied 48 times in a month. Removing rows whose window spans such an event moves the highest-qualified 1M mean from +21.06% to +4.67%, on 14 affected rows out of 1,411 -- one percent of the sample carrying three quarters of the published figure. Upper range moves +7.61% to +3.37%, Middle +13.19% to +5.71%, Lower +30.03% to +10.29%, and Lowest +75.62% to +5.51%. Every classification moves down. An existing quarantine reason, forward_return_out_of_range, could not catch this: its ceiling is 9,999.99%, so a 4,598% return is inside the bound. That constant stops arithmetic overflow and was never going to stop a corporate action. The detector added with this correction reads our own stored price series and refuses any window containing a single-session price factor at or beyond 5x in either direction, which no continuous market produces. It takes no view on which corporate action occurred; it only declines to call the window a return. Six hundred admitted registry rows across 55 tickers contain such a window, 259 of them resolved. Seven of the 55 are mega-caps -- AMAT, AMD, AXP, GE, HD, KLAC, MU -- where a five-fold single session is not a split but a bad print in our own stored series, which is disqualifying on the same grounds and is its own open defect. The rule is stated rather than tuned, and it lowers every number it touches, including the one this page led with. This entry said, from 2026-09-07, that every mean forward return published on this page was overstated. That was measured for the 1M column and written about the whole page. Measured for the 3M column on 2026-09-08 with the same query at 90 days: Middle range +9.72% becomes +9.77% once its 24 discontinuity-spanning rows are removed, and Upper range +9.52% becomes +10.35% once its 9 are -- both understated, not overstated. Lower range +3.85% becomes +3.57%. Two of the eight published means moved the other way, so the sentence was broader than its evidence and is left as first written, earlier in this entry, so a reader can see it. The highest-qualified 3M cell has one row and is not published.

600 registered rows across 55 tickers (AEHL, AEMD, AMAT, AMD, APUS, ARTL, AXP, BIAF, BIYA, BNRG, BRCC, BYAH, BYND, CCHH, CLDI, CLGN, CPOP, CSAI, CXAI, CYCU, DBGI, ELAB, FEED, FFAI, FGL, GAME, GCTK, GE, GLMD, GRML, GRNQ, HAO, HCWC, HD, IMCC, IPW, JDZG, JUNS, KAPA, KLAC, LEXX, LGCL, LGVN, LIMN, MBAI, MBRX, MU, MVIS, MYSZ, NCT, NRDY, NXL, OMH, ONFO, PLAG) spanned a stored-price change of at least 5x in either direction inside a forward window, out of 91,319 admitted rows (0.66%). 259 of them have resolved and sit inside the published evidence set, against 30,691 resolved rows in total (0.84%): Highest qualified 14, Upper range 53, Middle range 101, Lower range 56, Lowest range 35. The scores on those rows moved. Those rows are not restated. The registry admits nothing retroactively, so they stand as recorded and the correction applies to rows scored from Sep 7, 2026 onward.

Permanent citation

Sep 4, 2026: SEC SIC 6324 is "Hospital and Medical Service Plans". Veridion's SIC-to-sector crosswalk sent the whole 6000-6499 band to Financials, so nine managed-care insurers, UnitedHealth among them, carried Financials as their published sector. The crosswalk was corrected on 2026-09-03 and a deploy gate now fails any build in which a company's sector contradicts its SEC business code. What this did not change: the Veridion Score. Sector reaches the composite only by deciding whether a peer cohort may be used at all, and these rows were sector-sourced from SIC throughout, so that gate was open before the correction and after it. Valuation peers are selected by market-capitalisation tier rather than sector, and the hype peer cohort reads the curated universe, which already carried these issuers as Health Care. The scores on these rows are unchanged by the correction. The published sector was wrong, and that is what is corrected here. Nine issuers are affected, not the eight this entry first named: OSCR carries the same SEC code and was omitted from the first count. This entry also said, from 2026-09-04 to 2026-09-07, that none of the affected rows had resolved and that no forward return had landed on any registered row. Both were false when written. 106 of the affected rows had already resolved, inside a registry of 30,691 resolved rows -- the same total this page prints in its own header. The two figures were the only ones in this entry the published query never computed, so nobody could check them and nobody did. Every figure below is now produced by that query.

273 registered rows across 9 tickers (ALHC, CI, CLOV, CNC, ELV, HUM, MOH, OSCR, UNH) carried the wrong published sector, out of 91,319 admitted rows (0.30%). 106 of them have resolved and sit inside the published evidence set, against 30,691 resolved rows in total (0.35%): Highest qualified 22, Upper range 50, Middle range 31, Lower range 3. No published score moved: the correction changes the sector these rows are labelled with, not the number. Those rows are not restated. The registry admits nothing retroactively, so they stand as recorded and the correction applies to rows scored from Sep 4, 2026 onward.

Permanent citation