Update README.md

README.md

@@ -234,15 +234,13 @@ HF Inference Endpoints, or run as a subprocess in your data pipeline.
 
 ## Limitations and known gaps
 
-1. **`headcount` dimension is unreliable** (Spearman 0.39 vs frontier — 50% below the
-   other 9 topics). Treat with skepticism.
-2. **Tone has rank-order signal but absolute levels drift.** Quants should normalize
+1. **Tone has rank-order signal but absolute levels drift.** Quants should normalize
    cross-sectionally rather than thresholding raw values.
-3. **English transcripts only.** Non-English calls (translated) work but degrade. Top
+2. **English transcripts only.** Non-English calls (translated) work but degrade. Top
    non-US training countries: GB, DE, FR, JP, SE, CH, CN.
-4. **Truncates at 16,384 tokens.** Covers ~p99 of calls; the very longest (Asian
+3. **Truncates at 16,384 tokens.** Covers ~p99 of calls; the very longest (Asian
    conglomerates with 8h+ analyst days) lose middle content via head+tail truncation.
-5. **Pure NLP scorer — not an alpha model.** Outputs are *features*; the trading rule is
+4. **Pure NLP scorer — not an alpha model.** Outputs are *features*; the trading rule is
    the consumer's responsibility.
 
 ---