Statutory Interpretation as a Continuum and Equipoise in the Continuum (12/20/25)

Continuing on my exploration of AI (I am still a novice), I asked several AI tools about ambiguity and continuum of confidence in statutory interpretation as a way to think about when ambiguity does not permit a court to determine the best interpretation to the required confidence level (in percentages say 51%, 60%, 67%, etc.). I offer here the best of the AI outcomes (from MS CoPilot) with both text and footnotes indented and then make a few comments.

Below is a polished, law‑review‑style Part II that builds naturally on your Part I. It is structured, argumentative, and footnoted in proper Bluebook form. If you want, I can later add subparts (A, B, C), case studies, or integrate it into a full article.

II. The Ambiguity Continuum in Judicial Practice

Courts frequently describe statutory text as either “clear” or “ambiguous,” but this binary framing masks the far more nuanced reality of interpretive practice. In actual adjudication, judges encounter not a dichotomy but a continuum of ambiguity, ranging from provisions whose meaning is overwhelmingly apparent to those whose linguistic indeterminacy leaves multiple interpretations equally plausible.¹ Judicial methodology—whether textualist, purposivist, or something else—does not eliminate this continuum; rather, it structures how judges navigate it. Understanding this spectrum is essential to explaining why interpretive disputes persist even when judges purport to apply the same tools.

A. The Myth of Binary Clarity

The conventional judicial rhetoric of “plain meaning” suggests that statutory clarity is a threshold condition: either the text speaks for itself or it does not.² Yet linguistic theory and empirical studies of judicial behavior demonstrate that clarity is rarely self‑evident.³ Even seemingly straightforward provisions often contain latent ambiguities that become visible only when applied to specific factual contexts.⁴ As Justice Kagan has observed, “we’re all textualists now,” but textualism itself requires judges to make fine‑grained judgments about how much clarity is enough.⁵

These judgments are not mechanical. They depend on context, background assumptions, and the judge’s own interpretive priors.⁶ A provision may appear clear to one judge because she reads it against a particular linguistic or structural backdrop, while another judge—equally committed to textual fidelity—may find the same provision ambiguous.⁷ The very act of declaring a statute “clear” is thus an interpretive conclusion, not an objective fact.

B. Degrees of Ambiguity and the Use of Interpretive Tools

As ambiguity increases along the continuum, courts predictably rely more heavily on interpretive tools to resolve uncertainty. Textual canons, for example, function as probability‑adjusting heuristics: they shift the likelihood of one interpretation over another by appealing to linguistic conventions, structural coherence, or background norms.⁸ Legislative history, when used, serves a similar function by providing additional evidence about how Congress likely understood the statutory language.⁹ Substantive canons—such as the rule of lenity, the presumption against retroactivity, or federalism clear‑statement rules—operate at the far end of the continuum, where ambiguity is so deep that ordinary interpretive tools fail to produce a dominant reading.¹⁰

Importantly, these tools do not eliminate ambiguity; they manage it. They help courts decide when a statute is sufficiently clear to justify a particular outcome and when residual uncertainty warrants caution, deference, or a tie‑breaking presumption.¹¹ The very existence of these tools reflects judicial recognition that ambiguity is not a binary condition but a gradated one.

C. Judicial Disagreement as Evidence of the Continuum

The ambiguity continuum also helps explain persistent judicial disagreement. When judges diverge in their assessments of statutory meaning, the disagreement often stems not from methodological differences but from differing judgments about where on the continuum a particular provision falls.¹² For example, in Lockhart v. United States, the Supreme Court split over whether a limiting phrase modified only the immediately preceding term or the entire series—an interpretive dispute that turned on how ambiguous the text was and how much weight to give competing canons.¹³

Such disagreements are not aberrations; they are inherent to a system in which interpretive clarity is a matter of degree. Even within a single methodological framework, judges must make probabilistic assessments about linguistic meaning, contextual fit, and statutory purpose.¹⁴ These assessments inevitably vary across judges, producing the familiar pattern of fractured opinions in cases involving complex or open‑textured statutes.

D. The Continuum and Institutional Choice

Finally, recognizing the ambiguity continuum clarifies the institutional logic behind doctrines such as Chevron deference. Under Chevron Step One, courts ask whether Congress has “directly spoken to the precise question at issue.”¹⁵ This inquiry presupposes a threshold of clarity: if the statute is sufficiently clear, the court adopts its own interpretation; if not, the agency’s reasonable interpretation prevails.¹⁶ The doctrine thus operationalizes the ambiguity continuum by assigning interpretive authority based on degrees of clarity rather than a binary determination.

Similarly, doctrines like constitutional avoidance and lenity apply only when ambiguity persists after ordinary interpretive tools have been exhausted.¹⁷ These doctrines occupy the extreme end of the continuum, where no interpretation is more likely than not correct. Their very existence confirms that ambiguity is not an on‑off switch but a sliding scale that shapes judicial decision‑making.

Footnotes

1.   See Lawrence M. Solan, The Language of Judges 47–72 (1993) (explaining gradable ambiguity in legal texts).

2.   See, e.g., Conn. Nat’l Bank v. Germain, 503 U.S. 249, 253–54 (1992) (asserting that courts must give effect to the “plain meaning” of statutory text).

3.   See Solan, supra note 1, at 47–72.

4.   See Babbitt v. Sweet Home Chapter of Cmtys. for a Great Or., 515 U.S. 687 (1995).

5.   See Justice Elena Kagan, The Scalia Lecture: A Dialogue with Justice Kagan on the Reading of Statutes (Harvard Law School, Nov. 25, 2015).

6.   See Abbe R. Gluck, The States as Laboratories of Statutory Interpretation: Methodological Consensus and the New Modified Textualism, 119 Yale L.J. 1750, 1764–72 (2010).

7.   See John F. Manning, Textualism and the Equity of the Statute, 101 Colum. L. Rev. 1, 5–7 (2001).

8.   See Antonin Scalia & Bryan A. Garner, Reading Law: The Interpretation of Legal Texts 51–58 (2012).

9.   See Stephen Breyer, On the Uses of Legislative History in Interpreting Statutes, 65 S. Cal. L. Rev. 845, 848–49 (1992).

10.                See United States v. Santos, 553 U.S. 507, 514 (2008) (plurality opinion).

11.                See Henry M. Hart, Jr. & Albert M. Sacks, The Legal Process 1374–80 (William N. Eskridge, Jr. & Philip P. Frickey eds., 1994).

12.                See Gluck & Bressman, Statutory Interpretation from the Inside, 65 Stan. L. Rev. 901, 1003–05 (2013).

13.                Lockhart v. United States, 577 U.S. 347 (2016).

14.                See Adrian Vermeule, Judging Under Uncertainty 6–12 (2006).

15.                Chevron U.S.A. Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837, 842–43 (1984).

16.                See Cass R. Sunstein, Chevron Step Zero, 92 Va. L. Rev. 187, 191–95 (2006).

17.                See Clark v. Martinez, 543 U.S. 371, 381–82 (2005) (constitutional avoidance); Santos, 553 U.S. at 514 (lenity).

JAT Comments:

1. I need to clarify the word ambiguity because it is ambiguous. I mean in a statutory interpretation context that text is ambiguous when the court is in interpretive equipoise and unable to determine the best interpretation of the statute. In this sense, it is similar to factual equipoise, where the fact-finder is unable to determine the facts at the usual preponderance, more likely than not level.

2. My general impression is that the text presented above (rather than the footnotes) is a fair presentation of the topic.

3. I am not sure that the footnotes support the propositions for which they are cited. My spot-checking indicates that there are “hallucinations” in the footnotes which confirms my general understanding of the importance of double-checking citations.

4. One subject I was hoping to see in my AI adventures was a discussion of the continuum and confidence levels in percentages. For example, the more likely than not confidence level encountered in fact-finding is often conceptualized as confidence of at least 51% on the continuum spectrum. Can something like that be useful in statutory interpretation? If a court is at 50-50% as between interpretation A and interpretation B, the statutory text is ambiguous. How does the court break the tie? In fact-finding, the tie-breaker is resolved by the burden of persuasion. Lenity is often said to be a tie-breaker forcing defendant-friendly interpretations of ambiguous criminal laws. Is there a tie-breaker in statutory interpretation outside lenity? Perhaps the burden of persuasion can serve some role in legal interpretation disputes because the proponent bearing the burden of persuasion may be said to bear the risk of nonpersuasion on the facts and on the law in order to prevail. The problem is that the judicial decision in a legal dispute about interpretation resolves not only the facts which are usually specific to the case only but also the law applicable to the facts which may have some effect, precedential or persuasive, in other cases. Of course, Chevron served as the tie-breaker in disputes with agencies about statutory interpretation in Chevron-entitled guidance. But now, with Chevron rejected, what happens when a court is ambiguous about the interpretation of statutory text at the 50-50 level?

4. There is another issue in which I’m interested. Does ambiguity exist only at the 50-50 level? What if interpretation A is at 51% and interpretation B is at 49%? Is there a material difference between 51% and 49%? I think not and that rather that there is a range interpretive ambiguity where a court cannot meaningfully distinguish between interpretations in the range—say 55-45, 60-40 or 67-33.

5. Any number of judges and scholars note that, in fact-finding, equipoise is rare because the facts as presented and perceived by the fact-finder will permit the fact-finder to find the facts with at least 51% confidence. Can that be a useful analogy in law-finding? Is that what Loper Bright requires?

6. And this does not address situations where more than two interpretations are in play--within the range of interpretive ambiguity. For example, interpretation A at a confidence level of 37, interpretation B at a confidence level of 33 and interpretation C at a confidence level of 30. None have a confidence level of 51%, generally verbalized as more likely than not? But considered in relation only to one other alternative, interpretation A clearly is more likely than not compared to only interpretation B or C. Is that enough?