The question in Allstate Fire & Casualty Co. v. Love was whether “the amount of an insurancy policy or the underlying claim determines the amount in controversy to establish diversity jurisdiction ….” The Court addressed, and clarified, earlier Circuit precedent on that generaly topic, and went on to hold that in this case: “where the claim under the policy exceeds the value of the policy limit, courts … should ask whether there is a legal possibility that the insurer could be subject to liability in excess of the policy limit” (a Stowers claim having been made in this dispute). No. 22-20405 (June 22, 2023).

In United States v. Texas, last Friday, the Supreme Court reversed a Fifth Circuit judgment because Texas had no standing to bring a particular claim about immigration policy. The case echoes the proceedings in California v. Texas, a 2021 matter in which the Supreme Court also reversed a Fifth Circuit judgment for lack of standing — in that case, an issue about the enforceability of the Affordable Care Act.

As Texas’s Attorney General, Greg Abbott famously quipped: “I go into the office in the morning. I sue Barack Obama, and then I go home.” In a recent interview, I suggest that these opinions are a yellow light for that approach to public-law litigation; Mark Stern makes a similar point in more colorful language for Slate. Time will tell whether that traffic signal is heeded.

Two New York lawyers filed a brief with “fake law” in it, having accepted at face value a “hallucination” by ChatGPT abouot several cases that did not in fact exist. The district court has now sanctioned them. The opinion is of broad general interest, given the great influence of generative AI in its few short months of widespread public availability. And it’s also of broad general interest in avoiding sanctions–the lawyers had at least one good chance, and maybe even two, of coming clean about their error, but instead “doubled down” with purported screenshots of the nonexistent cases.

In a recent analysis of a sanctions order, the Fifth Circuit provided an instructive example of an argument that withstood a forfeiture objection:

“Ticket argues that CEATS forfeited the bad-faith argument by failing to assert it in the district court. While it is true that we tend not to entertain arguments that a party asserts for the first time on appeal, ‘an argument is not [forfeit]ed on appeal if the argument on the issue before the district court was sufficient to permit the district court to rule on it.’ Here, CEATS told the district court that a discovery violation ‘must be committed willfully or in bad faith for the court to award the severest remedies available under Rule 37(b).’ CEATS also argued that it did not violate the Protective Order willfully or in bad faith, because the ‘communications … were clearly inadvertent.’ That argument was enough to put the district court on notice that CEATS opposed any definition of ‘bad faith’ that includes inadvertent conduct.”

CEATS, Inc. v. TicketNetwork, Inc., No. 21-40705 (June 19, 2023) (citations and footnotes omitted). (This analysis has an interesting analog in the recent case of United Natural Foods, Inc. v. NLRB, where the majority and dissent disputed whether a particular issue was raised for purposes of the “party presentation” principle).

TicketNetwork, an online ticket marketplace, sued CEATS, a non-practicing IP company, for declarations that Ticket’s business did not violate CEATS’s patents or a related license agreement.

CEATS won at trial, and while its claim for attorneys fees was pending, obtained an order allowing it to see a list of Ticket’s website affiliates. That order restricted access to certain designated in-house representatives.

CEATS’s CEO, who was not supposed to see the list, then sent Ticket’s CEO a settlement demand–attaching the list. After significant proceedings, the district court awarded (1) a 30-month injunction against any dealings with the companies on the list and (2) $500,000 against CEATS, its CEO, and two litigation consultants.

The Fifth Circuit, inter alia:

• Vacated the award against the individuals: “The Individuals did not receive notice that monetary sanctions were pending against them, and they did not receive a pre-deprivation opportunity to defend themselves at a hearing. By the time the district court heard their response, it had already decided against them. That was an abuse of discretion.”
• Vacated the injunction: “We also agree with CEATS that the district court did not make the bad-faith finding that is a prerequisite to litigation-ending sanctions under [Fed. R. Civ. P.] 37(b). Instead, the district court found that CEATS acted recklessly, and then it equated recklessness with bad faith. We have rejected that equivalence.”
• Vacated the fee award: “[T]here was a significant disparity between the rates that the first court approved when it awarded attorney fees to CEATS (at an earlier stage of litigation) versus the rates that it approved when it awarded attorney fees to Ticket (as part of the sanction against CEATS).”

CEATS, Inc. v. TicketNetwork, Inc., No. 21-40705 (June 19, 2023). The Court aptly summarized: “We AFFIRM in (small) part, VACATE in (large) part, and REMAND for further proceedings.”

In Norsworthy v. Houston ISD, the Fifth Circuit acknowledged a recent amendment to Fed. R. App. P. 3(c) about the requirements for a notice of appeal.

In this case, the appellant’s notice of appeal named its Rule 59 motion to alter amend, not the final judgment itself. Under the earlier rule, that language could have given rise to a waiver issue. But a 2021 amendment says that “a notice of appeal encompasses the final judgment,” so long as the notice designates an order named in Fed. R. App. P. 4(a)(4)(A), which lists the standard post-trial motions. No. 22-20586 (June 13, 2023).

The Fifth Circuit was unwilling to extend a bankruptcy court’s “core” or “related-to” jurisdiction to reach a settlement agreement when:

“[T]he settlements contradict the plan. Whereas the plan discharged debts unless a timely proof of claim was filed, the settlements require Chesapeake to pay the non-filing lessors a portion of their royalty claims far higher than other creditors’ timely filed general unsecured claims. Whereas the plan assumed that Chesapeake’s leases would ride through bankruptcy unaffected, the settlement requires a mandatory alteration in the terms of thousands of Pennsylvania leases. Far from merely enforcing the plan, the settlement accomplished a self-described ‘fundamental reset of Chesapeake’s relationship with its Pennsylvania lessors.'”

No. 21-20232 (June 8, 2023).

The high-profile police-shooting case of Edwards v. City of Balch Springs ended with an affirmance of dismissal on qualified-immunity grounds. Among other holdings, the opinion succinctly captures the challenge in scrutinizing official use-of-force policies in this setting:

“[A] written policy is not facially unconstitutional just because it leaves out ‘detailed guidance that might have averted a constitutional violation.’ If it were otherwise, a use-of-force policy would be facially constitutional only if it recited every jot and tittle of the applicable caselaw. Surmounting that logistical hurdle would produce a behemoth free of any practical use—less a policy than a treatise.”

No. 22-10269 (June 9, 2023).  (The phrase “jot and tittle,” btw, has a Biblical origin related to pen strokes used to write Hebrew.)

Together with the able Raffi Melkonian from Houston, I presented the “Fifth Circuit Update” at the University of Texas appellate course last week; here is a copy of our PowerPoint.

An alleged requirements contract for a supply of auto parts did not satisfy the statute of frauds, when it did not say in writing that it was a requirements contract or otherwise establish a quantity, when:

• The email in question referenced a $10,000 credit limit (“Our credit manager is on the conservative side. He has given you a credit limit of $10K until he sees a credit history pattern. Your terms are net 30 days.t had a $10,000.”) The Fifth Circuit held: “The $10,000 figure is a credit limit; it is not a ‘specif[ication of] a quantity’ of goods that Wesden would buy from ITW.”
• The email attached a price list. The Court held: “Wesden contends that the attachment satisfies the quantity-term requirement because it shows that the parties agreed to an ‘”‘unlimited” quantity in writing, which is very specific.’ But this is not so. The attachment is an empty order form listing the per-unit price for each Auto Magic product. There is no quantity or exclusivity term in the price list.”

Wesdem LLC v. Illinois Tool Works, Inc., No. 22-50769 (June 9, 2023).

Jack Daniel’s v. VIP presented the question whether a dog toy, with the general appearance of a Jack Daniel’s bottle, infringed the Jack Daniel’s trademarks. The matter reached the Supreme Court because of a dispute over whether to (a) apply the customary likelihood-of-confusion factors under the Lanham Act, or (b) before applying those factors, apply “the Rogers test” that focuses on a First Amendent issue. The Supreme Court chose the simpler path and went straight to the factors:

Without deciding whether Rogers has merit in other contexts, we hold that it does not when an alleged infringer uses a trademark in the way the Lanham Act most cares about: as a designation of source for the infringer’s own goods. VIP used the marks derived from Jack Daniel’s in that way, so the infringement claim here rises or falls on likelihood of confusion. But that inquiry is not blind to the expressive aspect of the Bad Spaniels toy that the Ninth Circuit highlighted.

No. 22-148 (U.S. June 8, 2023) (citation omitted).

Longrunning litigation between the Allen Stanford receiver and a substantial Stanford investor came to an end in Janvey v. GMAG LLC, with the conclusion that the investor’s setoff defense had been forfeited.

The Fifth Circuit considered, but did not rule on, an argument based on the pretrial order. Reminding that “[a] pretrial order supersedes all pleadings,” the Fifth Circuit noted precedent that “even issues of law should be included in the pretrial order or else they are waived.” It was reluctant to apply that precedent here, however, when a joint stipulation said only that setoff would not be argued “during the trial of this matter.” The investor contended that setof was a legal matter that only became relevant after verdict.

But, held the Court, forfeiture occurred when the investor did not raise setoff in opposition to the receiver’s motion for entry of final judgment. No. 22-10235 (May 30, 2023).

Raskin v. Dallas ISD addresses whether a mother can sue, pro se, in federal court on behalf of her children under the Genetic Information Nondiscrimination Act. Acknowledging both the practical reality that many such actions must be brought pro se, and that the federal courts ordinarily require the professionalism of trained counsel, the majority opinion deftly read the relevant statutes to let the district court apply discretion to this issue on remand.

A dissent favored an absolute rule allowing such pro se proceedings, noting, inter alia, customs about pro se representation when the Judiciary Act was adopted in 1789. (to be fair, though, women such as Ms. Raskin did not have the ability to sue about much of anything in 1789, pro se or otherwise).

A recent Texas Lawbook article considers a new standing order by Hon. Brantley Starr about reliance on language-model AI programs when writing briefs. Judge Starr’s point is well-taken and Rule 11 should probably be revised to include a specific reference to this issue, given how pervasive these programs will likely become in the near future.

I asked ChatGPT what it thought about the matter (specifically: “What are the pros and cons of requiring attorneys to certify to the accuracy of court fiings made with the assistance of language-model AI programs, such as yourself?”) and here is what it had to say:

______

Introducing a requirement for attorneys to certify the accuracy of court filings made with the assistance of AI language models like GPT-4 could have several pros and cons. Here are some: