Openai/6924739c-2300-800e-9743-65c152c213f1

This conversation was exported from ChatGPT

gpt-5-1-thinking

User: review the attached for any indication of reference to legal authority from source outside the united states

review the attached for any indication of reference to legal authority from source outside the united states

Assistant: Short answer: I don’t see any legal authority cited from outside the United States in this brief.

Short answer: I don’t see any legal authority cited from outside the United States in this brief.

Here’s what I checked and what I found:

1. Table of Authorities – Cases - The cases listed are all from U.S. courts – U.S. Supreme Court, U.S. Courts of Appeals (2d, 3d, 6th, 9th, 11th, D.C. Cir.), U.S. District Courts, and similar, e.g.: - Campbell v. Acuff-Rose Music, Inc., 510 U.S. 569 (1994) - Google LLC v. Oracle Am., Inc., 593 U.S. 1 (2020) - Authors Guild v. Google, Inc., 804 F.3d 202 (2d Cir. 2015) - Dam Things from Denmark v. Russ Berrie & Co., 290 F.3d 548 (3d Cir. 2002) – note this is a Third Circuit decision; “from Denmark” is just part of the party’s name, not a foreign court. 2025-11-19-ROSS-Oppo-Redacted 2025-11-19-ROSS-Oppo-Redacted - I did not see any citations to foreign courts (e.g., UK courts, CJEU, Canadian Supreme Court, etc.) or to non-U.S. reporters.
2. Statutes and Rules - The jurisdictional and statutory references are to U.S. federal law, such as: - 28 U.S.C. §§ 1292, 1331, 1338 2025-11-19-ROSS-Oppo-Redacted - 17 U.S.C. provisions discussed throughout the brief. - Court rules cited are likewise U.S. rules (Fed. R. App. P., Fed. R. Civ. P., Third Circuit rules, etc.). 2025-11-19-ROSS-Oppo-Redacted I did not see any references to foreign statutes (e.g., UK CDPA, EU directives, civil codes from other countries).
3. Other Authorities - The “Other Authorities” section includes things like Nimmer on Copyright (a U.S. copyright treatise) and similar sources. 2025-11-19-ROSS-Oppo-Redacted - These are secondary sources but still U.S.-oriented; there are no international conventions (e.g., Berne Convention, TRIPS, WIPO treaties) or foreign law texts listed.
4. Body of the Brief - In the narrative sections (Statement of the Case, Argument, etc.), the legal analysis is built on the same U.S. authorities identified in the Table of Authorities and on U.S. statutory law. 2025-11-19-ROSS-Oppo-Redacted - I ran targeted searches within the document for terms that would typically signal foreign or international law (e.g., “Canada,” “United Kingdom,” “European,” “treaty,” “Berne,” “TRIPS,” “international,” “foreign law”) and did not find citations or discussion of non-U.S. legal regimes. 2025-11-19-ROSS-Oppo-Redacted
5. Non-U.S. names that are not foreign authority - The caption includes Thomson Reuters Enterprise Centre GmbH, and there is the case Dam Things from Denmark v. Russ Berrie & Co. mentioned above. Those references simply reflect party or corporate names (or foreign corporate forms), not foreign courts or foreign law being relied upon as authority. 2025-11-19-ROSS-Oppo-Redacted

Bottom line: All of the legal authorities actually cited as such in this brief are U.S. courts, U.S. statutes, U.S. rules, and U.S.-oriented secondary sources. I do not see any reliance on legal authority from a source outside the United States.

User: I'd like you to identify significant and highly relevant foreign authorities that the authors might have considered

I'd like you to identify significant and highly relevant foreign authorities that the authors might have considered

Assistant: Here are the foreign authorities that, in my view, are the most significant and directly relevant to the issues in the …

Here are the foreign authorities that, in my view, are the most significant and directly relevant to the issues in the ROSS / Thomson Reuters dispute (copyright in headnotes / digests, intermediate copying for AI training, and “research”/TDM-style exceptions).

I’ll group them by theme and flag the ones that are especially high-value for this case.

###

Why it matters here

• The Court held that headnotes, case summaries, topical indexes and the compilation of reported decisions are original works in which copyright subsists.
• It also set the “skill and judgment” test for originality (rejecting pure “sweat of the brow”), and developed a structured fair dealing framework (purpose, character, amount, alternatives, nature of work, effect).

Relevance to this case

• Direct analogue to Westlaw: CCH explicitly recognizes copyright in law-reporter headnotes, summaries, and indexes – the very sort of editorial content at issue here.
• Its fair-dealing analysis (especially the emphasis on “user’s rights” and technological neutrality) is a natural comparative reference point for U.S. fair use arguments about copying headnotes to support legal research tools.

What it held

• EBC publishes Supreme Court Cases (SCC) law reports. Defendants produced CD-ROM law databases alleged to have copied SCC’s materials.
• The Indian Supreme Court: - Agreed that headnotes, editorial notes, and some formatting/structural edits are copyright-protected; - Rejected copyright in the raw judgment text itself (public domain), but held that some copy-editing and structuring can reach the originality threshold; - Adopted the CCH “skill and judgment” standard, rejecting both pure sweat-of-the-brow and a high creativity threshold.

Relevance

• Factually very close: a law-report publisher vs. a digital legal research/database provider accused of using the publisher’s edited judgments and headnotes in electronic products.
• The court drew a line between public-domain judicial text and copyrightable editorial enhancements (headnotes, footnotes, paragraphing, introductions), then limited what could be freely reused.
• That structure maps closely onto arguments about what parts of Westlaw content ROSS could ingest, and whether copying for a competitor research platform is infringing.

What happened

• Reporters provided case reports for The Jurist; each report had a headnote summarizing the decision.
• The defendants published a monthly digest which reproduced headnotes/marginal notes from various reports (including The Jurist).
• The court held the plaintiffs had copyright in the reports, and the copying of the headnotes into the digest amounted to piracy.

Relevance

• Classic authority on copyright in law-report headnotes and on copying those headnotes into a separate digest product.
• Strong comparative support for Thomson Reuters’ side that headnotes and classification-style editorial content are protectable and can’t simply be taken into a competing system.

- Eastern Book Co. v LexisNexis injunction: later Indian proceedings confirmed injunctive protection for EBC’s law-report content against a competing legal database.

• David Vaver, “Copyright Inside the Law Library”: summarises Canadian law that publishers can object to copying of their headnotes, digests, and cumulative indices such as those in Dominion Law Reports.

These are secondary or follow-on, but they reinforce a transnational pattern: courts routinely protect law-report editorial matter separate from public-domain judgments.

###

Key holdings

• An 11-word extract of a protected work can be a “reproduction in part” if it embodies the author’s intellectual creation.
• Printing such snippets during a data-capture process is not a transient copy under InfoSoc Article 5(1); consent is required.

Relevance

• Shows how EU law treats intermediate copying in text-processing and data-capture workflows – very close to what happens in text and data mining or AI training.
• Supports the proposition that even small fragments of headnotes or key-number text can be protected, making wholesale ingestion for training a legally significant reproduction under EU standards.

Key points

• Concerned copyright in football fixture lists as databases.
• The CJEU held that a database is protected by copyright only if the selection or arrangement of data is the author’s own intellectual creation; investment in obtaining/checking data (“skill and labour”) alone isn’t enough.

Relevance

• Analogue for West’s key-number system and editorial classification: - To the extent U.S. courts are wrestling with how much originality is in a systematized legal digest, Football Dataco offers a fully worked-out “intellectual creation” vs mere labour framework.
• Also underscores that some structural, taxonomic choices in a legal database can be protectable, even when the underlying case law isn’t.

###

C-360/13 (CJEU, 2014) and [2013] UKSC 18

What it decided

• Considered whether online media-monitoring services and their clients infringed copyright by receiving and viewing snippets/links.
• The CJEU and UKSC held that the on-screen and cached copies made in ordinary web browsing fall within the InfoSoc “transient and incidental copy” exception and don’t require a licence.

Relevance

• Offers a nuanced foreign treatment of automated technical copies vs. more enduring reproductions in digital services.
• For ROSS-type systems, this line of authority helps frame arguments that some system-level copies are purely technical (and thus potentially excusable) while full-scale ingestion for training may go well beyond that transient category.

###

What the Directive does

• Introduces two TDM exceptions: - Art. 3 – mandatory exception for research organisations/cultural heritage institutions doing TDM for scientific research. - Art. 4 – broader exception allowing anyone to perform TDM unless rightsholders opt out using machine-readable reservations.
• Scholarship and policy analyses confirm these provisions were intended to cover automated analysis and AI training on large corpora.

Relevance

• This is the leading legislative model for handling AI-style training by exception rather than by fair use.
• It would have been a natural comparative touchstone for: - Arguing that when legislatures want to bless AI training on protected content, they do so expressly via TDM exceptions; - Or conversely, that absent such an exception, broad unlicensed training remains presumptively infringing.

What happened

• Photographer sued LAION over use of images scraped from the web and incorporated into an AI training dataset.
• The Hamburg court held that reproductions for training could fall under Germany’s TDM exception for scientific research (Section 60d UrhG, implementing DSM Art. 3), and that AI training counts as TDM.

Relevance

• One of the first court decisions squarely addressing AI training and TDM in Europe.
• Shows a judicial approach that: - Accepts AI training as TDM; - Uses statute-based exceptions rather than judge-made fair use; - Still leaves room for rightholder opt-outs and limits (especially when outputs reproduce works).

A U.S. court could look to this as a contrast model: in the EU, statutory exceptions + opt-outs are doing work that in the U.S. is being asked of fair use.

Key features

• Japan’s 2018 amendment created Article 30-4, which permits the use of copyrighted works for “information analysis”, including AI development and training, without needing authorisation, subject to certain conditions (for example, not using the works to enjoy them as such, and guarding against certain market harms).

Relevance

• Another major economy that has explicitly legalised AI training on copyright works via a broad TDM-style exception.
• Very useful as comparative material to show that where a jurisdiction wants to ensure AI training is lawful, it does so affirmatively—again reinforcing the idea that in the U.S., courts are being asked to fill a policy gap via fair use.

What it says

• Section 29A allows making copies of works for text and data analysis for non-commercial research, provided the user has lawful access to the work.
• There has been active UK discussion about broadening this into an EU-style TDM exception that would more clearly cover AI training.

Relevance

• For Westlaw-style subscription access, this is particularly on point: - It suggests a model where lawful subscribers can data-mine content in limited research contexts without permission, but commercial exploitation (like building a competing product) remains contested or excluded.
• It’s a neat comparative frame for where ROSS-type uses might sit if this were litigated under UK law.

These are less about headnotes specifically but very relevant to fair use / fair dealing analysis of AI training.

- The Supreme Court held that 30–90 second music previews offered by online stores were fair dealing for the purpose of “research” under s. 29 of the Copyright Act, even in a commercial setting.

• The Court emphasised: - A “large and liberal” interpretation of “research”; - That fair dealing is a user’s right; - The importance of technological neutrality.

Relevance

• Supports arguments that automated, intermediate copying that enables users’ research (like training a legal research AI) can be consistent with a robust user-rights conception, especially where: - Outputs don’t substitute for the original work; - The dealing may promote access to law and legal information.

- Clarified that downloading a digital copy engages the reproduction right but not a separate “communication to the public” right, highlighting the principle of technological neutrality in Canadian copyright.

Relevance

• Not about TDM per se, but supports a comparative approach that looks at the substance of what’s happening (creating copies for a new use) rather than the technical form — helpful analogical material for fair-use arguments about intermediate copies during AI training.

If you only had room for a handful of foreign authorities that are both substantively on-point and likely to be treated as serious comparative law by a U.S. federal court, I’d prioritise:

1. CCH Canadian Ltd v Law Society of Upper Canada (Canada) – for both - copyright in headnotes / law-report enhancements, and - a structured, user-rights-oriented fair dealing framework.
2. Eastern Book Company v D.B. Modak (India) – nearly a factual cousin to Thomson Reuters v ROSS: law report publisher vs digital database; headnotes and edited judgments; adoption of the CCH originality test.
3. Sweet v Benning (UK) – historic but very on-point authority on copying headnotes into a digest, supporting strong protection for law-report editorial content.
4. Infopaq (C-5/08) and Football Dataco (C-604/10) (EU/CJEU) – together they give a sophisticated foreign view on: - How small fragments (11 words) can be protected at the reproduction stage; - How selection/arrangement originality in a database is evaluated.
5. DSM Directive Arts. 3–4 + Hamburg/LAION decision – to show that when AI training is meant to be privileged, many jurisdictions rely on explicit TDM exceptions (sometimes with opt-outs) rather than stretching general fair-use doctrines.
6. Japan’s Article 30-4 – as a contrasting legislative choice to affirmatively permit broad AI training uses of copyrighted works.
7. Optionally, SOCAN v Bell Canada – if you want a common-law Supreme Court decision aggressively expanding “research” and user rights in a technologically complex, commercial context.

If you tell me which side of the case you’re supporting (ROSS or Thomson Reuters), I can help narrow this down further into “good for us, bad for them” buckets and suggest how each authority could be framed rhetorically.

User: Having regard the norms of US jurisprudence and practice, as well as to litigation strategy, why might TR have chosen t…

Having regard the norms of US jurisprudence and practice, as well as to litigation strategy, why might TR have chosen to omit any reference to the CCH case from the apex court of a jurisdiction with similar legal system?

Assistant: Short version: CCH is a double-edged sword for Thomson Reuters.

Short version: CCH is a double-edged sword for Thomson Reuters. The parts that help them (copyright in headnotes and law reports) come bundled with a very user-friendly, research-protective fair-dealing framework and strong rhetoric about access to legal information—exactly the kind of thing ROSS would love to put in front of a U.S. court. Given U.S. norms about foreign law and basic appellate-strategy constraints, it’s pretty rational to leave CCH on the cutting-room floor.

Here’s a more structured breakdown.

1. U.S. norms about foreign decisions

a. Foreign cases are, at best, weak persuasive authority

In U.S. federal courts:

• Binding: U.S. Supreme Court, relevant circuit, and sometimes state courts on state law.
• Persuasive: other circuits, district courts, and then way down the ladder foreign courts.

So if you’re TR, you already have:

• Feist and its progeny on originality;
• U.S. cases recognizing copyright in headnotes / editorial material;
• A robust U.S. fair-use framework you can try to shape in your favor.

Adding CCH doesn’t change the binding law; it just gives the court extra reading and a chance to say “Canadian law is interesting but not controlling.” That’s a poor use of limited brief space unless the foreign case gives you something you can’t get from U.S. law.

b. Skepticism about foreign law, especially outside specialized areas

Some U.S. judges are openly wary of foreign citations except where international/foreign law is inherently at issue (e.g., treaties, international arbitration, maritime, choice-of-law questions).

Here you’re in a straight U.S. copyright / fair use case. Citing a Canadian Supreme Court decision could:

• Invite a “why are you bringing me Canadian law?” reaction.
• Signal (fairly or unfairly) that you don’t have enough domestic support.
• Distract from what you want to hammer: U.S. statutory language and U.S. Supreme Court precedent.

For a big commercial plaintiff like TR, playing it doctrinally orthodox (U.S. sources only) is often safer.

2. CCH is substantively mixed for TR

CCH is not just a “yay publishers” decision. It’s a carefully balanced, user-friendly opinion. TR would not control which parts the court focuses on.

a. Yes, CCH helps on originality in law reports

Good for TR:

• CCH recognizes that headnotes, case digests, indices, and other editorial enhancements are original works and protected by copyright.
• It rejects pure “sweat of the brow” but still finds sufficient “skill and judgment” in law-report editing.

That dovetails nicely with TR’s claim that Westlaw’s headnotes, key numbers, and editorial content are protectable, even though the underlying judicial opinions are public domain.

But…

b. CCH strongly emphasises user rights and research uses

Bad (or at least risky) for TR:

• CCH characterizes fair dealing as a “user’s right”, not merely a defence.
• It interprets “research” very broadly and analogizes fair dealing to a constitutional-style balancing of access and protection.
• It ultimately finds that the Law Society’s custom photocopy service for legal research was fair dealing, despite systematic copying.

That is a narrative ROSS would happily import:

• “Just as CCH treated the law library’s copying as user-oriented research, this AI system enables legal research; the real beneficiaries are lawyers and the public.”
• “CCH shows that even substantial copying of law-report material can be fair when it serves research and access-to-law purposes.”

Once CCH is on the table, the court will read the whole thing, not just the paragraph TR likes. TR may decide that the upside (more support for originality) is outweighed by the downside (comparative support for expansive research exceptions).

c. CCH’s originality standard can cut both ways

CCH adopts a “skill and judgment” standard for originality, which is consciously similar to what Feist actually requires in U.S. law.

From TR’s perspective:

• They already must confront Feist and argue: “Our headnotes and key-number system aren’t mere facts or mechanical edits; they reflect judgment and creativity.”
• CCH emphasises that not everything a law reporter does is protectable—there has to be intellectual effort beyond the inevitable and commonplace.

ROSS could seize on that:

• “Even Canada’s apex court, while recognizing some editorial copyright, warns against over-protecting routine editorial work that would lock up access to law.”
• “Under a Feist-like standard, much of the classification work is not protectable expression.”

So CCH may not give TR more originality mileage than they already get from U.S. cases, but it does give ROSS extra language about limiting protection.

3. Fair dealing vs fair use: TR may not want that comparison

Although fair dealing (Canada) and fair use (U.S.) overlap, there are important structural and rhetorical differences.

a. CCH builds a structured, user-friendly fair-dealing test

CCH sets out:

• Enumerated purposes (research, private study, etc.) interpreted broadly;
• A multi-factor fairness analysis with strong pro-user framing.

ROSS would argue:

• “Look—another common-law high court has adopted a structured, liberal, research-protective framework for analyzing informational uses. The U.S. should interpret fair use in a similar, research-friendly way, especially for legal information.”

TR does not want to invite that comparison. Their ideal framing:

• Treat fair use as a narrow, fact-bound exception, not a user-right.
• Focus on commerciality, market substitution, and the scale of copying.
• Keep the debate centered on U.S. four-factor case law that can be argued to cut against large-scale, commercial training on valuable proprietary databases.

Bringing in CCH risks encouraging the court to import user-rights rhetoric into U.S. fair-use analysis.

4. Litigation-strategy and briefing constraints

Even if CCH were modestly helpful, there are mundane but real strategic reasons to drop it.

a. Word limits and focus

Federal appellate briefs are constrained by strict word limits. Good appellate writing is about relentless prioritization:

• Lead with binding Supreme Court and circuit authority.
• Use persuasive authority sparingly.
• Avoid side-roads that force the court to learn a foreign doctrinal system.

A Canadian Supreme Court case that:

• Isn’t binding,
• Has mixed pro-publisher and pro-user language,
• Uses a different statutory scheme and doctrinal framing,

is exactly the kind of thing that can be cut in favor of doubling down on U.S. authorities (e.g., Google v. Oracle, Authors Guild v. Google, circuit decisions on databases and compilations, etc.).

b. Avoid giving the other side easy ammo

The moment TR cites CCH, they give ROSS:

• License to quote all of CCH’s user-rights, access-to-law, and research-friendly language back at the same court;
• A justification to bring in other foreign authorities (EU, India, Japan) on text and data mining and AI training, many of which are more sympathetic to training-based uses.

From TR’s perspective:

• They’d rather argue: “This case can be cleanly resolved under U.S. law; you don’t need to open the door to a global policy debate about AI training.”
• They know ROSS would happily say: “Once we’re doing comparative law, let’s talk about EU TDM exceptions and Japan’s AI-friendly statutes.”

So strategically, keeping the playground fenced to U.S. law is advantageous for TR.

c. Perception of cherry-picking foreign law

If you cite CCH only for “headnotes are copyright” and stay silent on its fair-dealing and access-to-law parts, you risk:

• A judge or clerk reading the rest and concluding you’re cherry-picking.
• Undermining your credibility on other citations.

Many experienced litigators are cautious about inviting that kind of “I read the whole case and you did not give me the full story” reaction—especially when the case is foreign and the court doesn’t know it already.

5. Similar legal system ≠ automatic relevance

You specifically mentioned that Canada is a similar legal system. That’s true (same common-law heritage), but from a U.S. appellate perspective:

• Similarity helps with intelligibility (judges can read and understand the reasoning).
• It does not change the fact that Canadian law is non-binding and built on a different statute, with different policy choices baked in.

A U.S. court might find CCH interesting in an academic sense. But TR’s job is not to educate the court on comparative copyright; it is to win under U.S. law with a focused, tightly-argued brief.

Given that:

• The “similar system” argument is more useful to ROSS (to say “look, other common-law jurisdictions are pro-research / pro-TDM”), and
• TR already has enough domestic material to make the originality point,

it’s unsurprising they’d decide not to go there.

6. Putting it all together

If you fold in U.S. jurisprudential norms and hard-nosed litigation tactics, TR might rationally conclude:

1. Marginal doctrinal gain CCH gives them only incremental support on originality and protection of headnotes—support they can already ground in U.S. cases and Feist-compatible arguments.
2. Significant strategic downside CCH simultaneously strengthens the narrative that copying legal materials for research and access to law can be lawful, user-protective, and socially valuable, which aligns more with ROSS’s framing than TR’s.
3. Risk of foreign-law distractions Citing it invites comparative law discussion, potential judicial skepticism, and an open door for ROSS to bring in foreign pro-AI/TDM authorities.
4. Brief economy and credibility With limited words and the need to appear grounded in U.S. doctrine, a foreign case with a mixed message is an easy candidate to cut.

So, even though CCH comes from a respected apex court in a similar legal tradition, from TR’s standpoint it’s a strategic minefield: too much rhetorical upside for ROSS and not enough doctrinal upside for TR to justify the risk.