This week’s Footnotes Season Finds report highlights Bristol Myers Squibb’s understated reported earnings and its cheap stock valuation. It is just one of the many interesting discoveries from the 190 10-Ks and 10-Qs our Robo-Analyst AI[1] analyzed in the first, short week of Footnotes Season.

Filing Season Finds reports are available only to Pro and Institutional members. More of the insights revealed by our Robo-Analyst technology during Filing Season are available here. Since 2005, we’ve reported how traditional earnings measures are unreliable due to accounting loopholes that allow companies to manage earnings. Our proprietary Core Earnings exclude unusual gains and losses to provide a more reliable earnings measure and a new source of alpha.

You need a Professional Membership or higher to view all the content on this page.

Already a member?

Learn more about our research here.

The Power of the Robo-Analyst

From the 190 10-K and 10-Q filings analyzed by our Robo-Analyst in the first week of Footnotes Season (began February 12, 2026), we collected 21,571 data points. This data led to 3,295 Core Earnings, balance sheet, and valuation adjustments with a combined dollar value of $3.3 trillion. The adjustments were applied as follows:

  • 1,348 income statement adjustments with a total value of $190 billion
  • 1,277 balance sheet adjustments with a total value of $1.3 trillion
  • 670 valuation adjustments with a total value of $1.8 trillion

Figure 1: Footnotes Season Diligence for 2025 10-K Footnotes Season: Feb-Mar 2026

Sources: New Constructs, LLC and company filings.

Every year from mid-February through early March, we parse and analyze over 2,000 10-Ks and 10-Qs to update our models for companies with 12/31 and 1/31 fiscal year ends. This combination of technology and human expertise enables investors to overcome the flaws in legacy fundamental research and make more informed investment decisions.

Proprietary Footnotes Data Drives Alpha

While we’re explaining the diligence required to calculate Core Earnings and generate proven-superior Stock Ratings, we want to show you how both deliver alpha. We’ve developed multiple indices with Bloomberg’s Index Licensing Group that track based on Core Earnings and our Stock Ratings. See Figures 2-4.

  1. Bloomberg New Constructs Core Earnings Leaders Index (ticker: BCORET:IND)
  2. Bloomberg New Constructs Ratings VA-1 Index (ticker: BNCVA1T:IND)
  3. Bloomberg New Constructs 500 Index (ticker: B500NCT:IND)

The Bloomberg New Constructs Core Earnings Leaders Index, which allocates based on Earnings Capture and Core Earnings, beat the S&P 500 by over 30% over the past five years. The Index (ticker: BCORET:IND) was up 111% while the S&P 500 was up 81%.

Figure 2: Bloomberg New Constructs Core Earnings Leaders Index Outperforms S&P 500: Last 5 Years

Sources: Bloomberg as of February 20, 2026
Note: Past performance is no guarantee of future results.

The “Very Attractive Stocks” Index, which allocates to stocks that get a Very Attractive rating by our AI Agent for Investing, beat the S&P 500 by 36% over the last five years. Bloomberg’s official name for the index is Bloomberg New Constructs Ratings VA-1Index (ticker: BNCVAT1T:IND). Figure 3 shows it was up 117% while the S&P 500 was up 81%.

Figure 3: Very Attractive-Rated Stocks Strongly Outperform the S&P 500: Last Five Years

Sources: Bloomberg as of February 20, 2026
Note: Past performance is no guarantee of future results.

Our “Core-Earnings Weighted S&P 500” Index, which weights the largest 500 U.S. companies by Core Earnings instead of market cap, beat the S&P 500 by 24% over the past five years. Bloomberg’s official name for the index is Bloomberg New Constructs 500 Total Return Index (ticker: B500NCT:IND). Figure 4 shows it was up 105% while the S&P 500 was up 81%.

Figure 4: Bloomberg New Constructs 500 Index Strongly Outperforms the S&P 500: Last Five Years

Sources: Bloomberg as of February 20, 2026
Note: Past performance is no guarantee of future results.

This article was originally published on February 24, 2026.

Disclosure: David Trainer, Garrett O’Grady, and Kyle Guske II receive no compensation to write about any specific stock, sector, style, or theme.

Questions on this report or others? Join our online community and connect with us directly.

[1] Harvard Business School features the powerful impact of our research automation technology in New Constructs: Disrupting Fundamental Analysis with Robo-Analysts.