Each company represents an independent path to YES resolution (either signing suffices), so we forecast each separately and combine with independent_or. Research focuses on confirming current signatory status and any signals of intent to join the voluntary pledge.
## Cross-Market Signals ### No signal found
1. [sq1 | web_search | STRONG cred 85 | DOWN | DATED] Anthropic was not among the 115 initial EU AI Pact signatories in September 2024 and did not sign. 2. [sq1 | web_search | MODERATE cred 70 | NEUTRAL | RECENT] Over 230 companies have since signed the AI Pact pledges, but Anthropic is not confirmed among the current signatories. 3. [sq1 | web_search | MODERATE cred 80 | UP | DATED] Anthropic did sign the separate EU GPAI Code of Practice (July 2025), showing willingness to engage with EU AI regulatory frameworks. 4. [sq2 | web_search | STRONG cred 85 | DOWN | DATED] Mistral AI was not among the initial EU AI Pact signatories in September 2024. 5. [sq2 | web_search | MODERATE cred 80 | UP | DATED] Mistral AI signed the EU GPAI Code of Practice among the first signatories (July 2025) with no chapter limitation. 6. [sq2 | article_search | WEAK cred 65 | UP | RECENT] Mistral CEO Mensch frames Europe/AI as a strategic asset and positions Mistral as Europe's frontier lab, aligned with EU priorities. 7. [sq2 | article_search | WEAK cred 70 | NEUTRAL | RECENT] Mistral is expanding EU infrastructure (Sweden data centers, $830M debt financing) emphasizing European AI autonomy. 8. [sq1 | web_search | STRONG cred 85 | DOWN | RECENT] The AI Pact and GPAI Code of Practice are distinct instruments; GPAI signing does not automatically place a company on the AI Pact list. ## Cross-Market Signals ### No signal found Information gaps: - No confirmed current (2026) AI Pact signatory list showing/excluding Anthropic or Mistral - No stated intent by either firm to join AI Pact specifically - Base rate for late-joiners adding to the AI Pact list over time - Whether GPAI signatories tend to also sign the AI Pact Key uncertainties: - Whether either firm sees value in AI Pact given they already signed GPAI Code - Timing of any signature relative to Sept 1, 2026 deadline - Anthropic's overall strategic reluctance to non-binding EU pledges - Mistral's EU-alignment incentives potentially driving a signature
You are an elite superforecaster using Tetlock-style Fermi decomposition. Estimate each sub-question INDEPENDENTLY, then provide a holistic estimate. The pipeline will mathematically recombine the sub-question estimates — your job is to give the most accurate per-component probabilities.
## Question
Will Anthropic or Mistral AI sign the European Commission's AI Pact before September 1, 2026?
## Description / Resolution Criteria
## Description
According to the resolution source, "The EU AI Pact voluntary pledges call on participating companies to commit to at least three core actions:
Adopting an AI governance strategy to foster the uptake of AI in the organisation and work towards future compliance with the AI Act
Identifying and mapping AI systems likely to be categorised as high-risk under the AI Act
Promoting AI awareness and literacy among staff, ensuring ethical and responsible AI development"
`{"format": "bot_tournament_question", "info": {"hash_id": "3ea566f33105cc2b", "sheet_id": "92"}}`
## Resolution Criteria
This question resolves as **Yes** if, before September 1, 2026, Anthropic or Mistral AI appear at the AI Pact [Signatories of the pledges](https://digital-strategy.ec.europa.eu/en/policies/ai-pact#ecl-inpage-Signatories-of-the-AI-Pact) list maintained by the European Commission.
## Sub-question decomposition
- (w=0.50) Will Anthropic appear on the EU AI Pact signatories list before September 1, 2026? — Anthropic is a US-based frontier AI lab; its participation in the voluntary EU AI Pact is one of two independent paths t
- (w=0.50) Will Mistral AI appear on the EU AI Pact signatories list before September 1, 2026? — Mistral is a French AI company with strong EU ties and regulatory alignment incentives, making it plausibly more likely
Combination rule: **independent_or**
## Synthesized evidence
1. [sq1 | web_search | STRONG cred 85 | DOWN | DATED] Anthropic was not among the 115 initial EU AI Pact signatories in September 2024 and did not sign.
2. [sq1 | web_search | MODERATE cred 70 | NEUTRAL | RECENT] Over 230 companies have since signed the AI Pact pledges, but Anthropic is not confirmed among the current signatories.
3. [sq1 | web_search | MODERATE cred 80 | UP | DATED] Anthropic did sign the separate EU GPAI Code of Practice (July 2025), showing willingness to engage with EU AI regulatory frameworks.
4. [sq2 | web_search | STRONG cred 85 | DOWN | DATED] Mistral AI was not among the initial EU AI Pact signatories in September 2024.
5. [sq2 | web_search | MODERATE cred 80 | UP | DATED] Mistral AI signed the EU GPAI Code of Practice among the first signatories (July 2025) with no chapter limitation.
6. [sq2 | article_search | WEAK cred 65 | UP | RECENT] Mistral CEO Mensch frames Europe/AI as a strategic asset and positions Mistral as Europe's frontier lab, aligned with EU priorities.
7. [sq2 | article_search | WEAK cred 70 | NEUTRAL | RECENT] Mistral is expanding EU infrastructure (Sweden data centers, $830M debt financing) emphasizing European AI autonomy.
8. [sq1 | web_search | STRONG cred 85 | DOWN | RECENT] The AI Pact and GPAI Code of Practice are distinct instruments; GPAI signing does not automatically place a company on the AI Pact list.
## Cross-Market Signals
### No signal found
Information gaps:
- No confirmed current (2026) AI Pact signatory list showing/excluding Anthropic or Mistral
- No stated intent by either firm to join AI Pact specifically
- Base rate for late-joiners adding to the AI Pact list over time
- Whether GPAI signatories tend to also sign the AI Pact
Key uncertainties:
- Whether either firm sees value in AI Pact given they already signed GPAI Code
- Timing of any signature relative to Sept 1, 2026 deadline
- Anthropic's overall strategic reluctance to non-binding EU pledges
- Mistral's EU-alignment incentives potentially driving a signature
## Required pre-forecast walkthrough
Before giving probabilities, walk through these explicitly:
(a) The time left until the question resolves.
(b) The status quo outcome — what happens if nothing changes from today.
(c) A brief scenario that results in NO.
(d) A brief scenario that results in YES.
## Calibration guidance
- **Estimate each sub-question in isolation.** Do not let your answer to one sub-question anchor your answer to another. This is the core of Fermi decomposition — independence forces more careful reasoning per factor.
- **Anchor on the status quo.** Require strong specific evidence to move far from it.
- 0.05 / 0.95 require strong, multi-source evidence. Avoid >0.97 or <0.03 unless the outcome is already settled or near-tautological — overconfident misses are punished heavily by the log score.
- **Anchor on prediction markets.** If liquid market prices (Polymarket / Kalshi) or a community forecast appear in the evidence, treat them as a strong, well-calibrated prior. Your final estimate should rarely sit more than ~15 percentage points from a liquid market on the SAME question — move further only with specific evidence the market lacks.
- **Treat research as fallible, not ground truth.** A single-source or "very recent" claim — especially one the evidence flags as unverified, possibly AI-generated, or low-credibility — must not drive you to near-certainty. When a load-bearing fact is unverified, keep at least 10-15% on the chance it is wrong.
- **Also provide a holistic estimate** — your overall gut feeling about the main question, BEFORE you see the mathematical combination. This serves as a sanity check: if the Fermi result and holistic estimate diverge wildly, something is wrong.
## Output
Return ONLY valid JSON, no markdown fences:
{
"rationale": "<address (a) (b) (c) (d) above — 5-8 sentences total>",
"sub_question_estimates": {
"sq1": <float in [0.01, 0.99]>,
"sq2": <float in [0.01, 0.99]>
},
"holistic_p_yes": <float in [0.01, 0.99] — your overall estimate ignoring the decomposition>,
"what_would_change_my_mind": "<1-2 sentences: what new info would push you above 70% or below 30%>"
}
{
"forecast": {
"combination_logic": "independent_or",
"evidence_brief": "1. [sq1 | web_search | STRONG cred 85 | DOWN | DATED] Anthropic was not among the 115 initial EU AI Pact signatories in September 2024 and did not sign.\n2. [sq1 | web_search | MODERATE cred 70 | NEUTRAL | RECENT] Over 230 companies have since signed the AI Pact pledges, but Anthropic is not confirmed among the current signatories.\n3. [sq1 | web_search | MODERATE cred 80 | UP | DATED] Anthropic did sign the separate EU GPAI Code of Practice (July 2025), showing willingness to engage with EU AI regulatory frameworks.\n4. [sq2 | web_search | STRONG cred 85 | DOWN | DATED] Mistral AI was not among the initial EU AI Pact signatories in September 2024.\n5. [sq2 | web_search | MODERATE cred 80 | UP | DATED] Mistral AI signed the EU GPAI Code of Practice among the first signatories (July 2025) with no chapter limitation.\n6. [sq2 | article_search | WEAK cred 65 | UP | RECENT] Mistral CEO Mensch frames Europe/AI as a strategic asset and positions Mistral as Europe\u0027s frontier lab, aligned with EU priorities.\n7. [sq2 | article_search | WEAK cred 70 | NEUTRAL | RECENT] Mistral is expanding EU infrastructure (Sweden data centers, $830M debt financing) emphasizing European AI autonomy.\n8. [sq1 | web_search | STRONG cred 85 | DOWN | RECENT] The AI Pact and GPAI Code of Practice are distinct instruments; GPAI signing does not automatically place a company on the AI Pact list.\n\n## Cross-Market Signals\n\n### No signal found\n\nInformation gaps:\n - No confirmed current (2026) AI Pact signatory list showing/excluding Anthropic or Mistral\n - No stated intent by either firm to join AI Pact specifically\n - Base rate for late-joiners adding to the AI Pact list over time\n - Whether GPAI signatories tend to also sign the AI Pact\n\nKey uncertainties:\n - Whether either firm sees value in AI Pact given they already signed GPAI Code\n - Timing of any signature relative to Sept 1, 2026 deadline\n - Anthropic\u0027s overall strategic reluctance to non-binding EU pledges\n - Mistral\u0027s EU-alignment incentives potentially driving a signature",
"forecast_prompt": "You are an elite superforecaster using Tetlock-style Fermi decomposition. Estimate each sub-question INDEPENDENTLY, then provide a holistic estimate. The pipeline will mathematically recombine the sub-question estimates \u2014 your job is to give the most accurate per-component probabilities.\n\n## Question\nWill Anthropic or Mistral AI sign the European Commission\u0027s AI Pact before September 1, 2026?\n\n## Description / Resolution Criteria\n## Description\nAccording to the resolution source, \"The EU AI Pact voluntary pledges call on participating companies to commit to at least three core actions:\n\nAdopting an AI governance strategy to foster the uptake of AI in the organisation and work towards future compliance with the AI Act\nIdentifying and mapping AI systems likely to be categorised as high-risk under the AI Act\nPromoting AI awareness and literacy among staff, ensuring ethical and responsible AI development\"\n\n`{\"format\": \"bot_tournament_question\", \"info\": {\"hash_id\": \"3ea566f33105cc2b\", \"sheet_id\": \"92\"}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if, before September 1, 2026, Anthropic or Mistral AI appear at the AI Pact [Signatories of the pledges](https://digital-strategy.ec.europa.eu/en/policies/ai-pact#ecl-inpage-Signatories-of-the-AI-Pact) list maintained by the European Commission.\n\n## Sub-question decomposition\n- (w=0.50) Will Anthropic appear on the EU AI Pact signatories list before September 1, 2026? \u2014 Anthropic is a US-based frontier AI lab; its participation in the voluntary EU AI Pact is one of two independent paths t\n- (w=0.50) Will Mistral AI appear on the EU AI Pact signatories list before September 1, 2026? \u2014 Mistral is a French AI company with strong EU ties and regulatory alignment incentives, making it plausibly more likely \n\nCombination rule: **independent_or**\n\n## Synthesized evidence\n1. [sq1 | web_search | STRONG cred 85 | DOWN | DATED] Anthropic was not among the 115 initial EU AI Pact signatories in September 2024 and did not sign.\n2. [sq1 | web_search | MODERATE cred 70 | NEUTRAL | RECENT] Over 230 companies have since signed the AI Pact pledges, but Anthropic is not confirmed among the current signatories.\n3. [sq1 | web_search | MODERATE cred 80 | UP | DATED] Anthropic did sign the separate EU GPAI Code of Practice (July 2025), showing willingness to engage with EU AI regulatory frameworks.\n4. [sq2 | web_search | STRONG cred 85 | DOWN | DATED] Mistral AI was not among the initial EU AI Pact signatories in September 2024.\n5. [sq2 | web_search | MODERATE cred 80 | UP | DATED] Mistral AI signed the EU GPAI Code of Practice among the first signatories (July 2025) with no chapter limitation.\n6. [sq2 | article_search | WEAK cred 65 | UP | RECENT] Mistral CEO Mensch frames Europe/AI as a strategic asset and positions Mistral as Europe\u0027s frontier lab, aligned with EU priorities.\n7. [sq2 | article_search | WEAK cred 70 | NEUTRAL | RECENT] Mistral is expanding EU infrastructure (Sweden data centers, $830M debt financing) emphasizing European AI autonomy.\n8. [sq1 | web_search | STRONG cred 85 | DOWN | RECENT] The AI Pact and GPAI Code of Practice are distinct instruments; GPAI signing does not automatically place a company on the AI Pact list.\n\n## Cross-Market Signals\n\n### No signal found\n\nInformation gaps:\n - No confirmed current (2026) AI Pact signatory list showing/excluding Anthropic or Mistral\n - No stated intent by either firm to join AI Pact specifically\n - Base rate for late-joiners adding to the AI Pact list over time\n - Whether GPAI signatories tend to also sign the AI Pact\n\nKey uncertainties:\n - Whether either firm sees value in AI Pact given they already signed GPAI Code\n - Timing of any signature relative to Sept 1, 2026 deadline\n - Anthropic\u0027s overall strategic reluctance to non-binding EU pledges\n - Mistral\u0027s EU-alignment incentives potentially driving a signature\n\n## Required pre-forecast walkthrough\n\nBefore giving probabilities, walk through these explicitly:\n (a) The time left until the question resolves.\n (b) The status quo outcome \u2014 what happens if nothing changes from today.\n (c) A brief scenario that results in NO.\n (d) A brief scenario that results in YES.\n\n## Calibration guidance\n\n- **Estimate each sub-question in isolation.** Do not let your answer to one sub-question anchor your answer to another. This is the core of Fermi decomposition \u2014 independence forces more careful reasoning per factor.\n- **Anchor on the status quo.** Require strong specific evidence to move far from it.\n- 0.05 / 0.95 require strong, multi-source evidence. Avoid \u003e0.97 or \u003c0.03 unless the outcome is already settled or near-tautological \u2014 overconfident misses are punished heavily by the log score.\n- **Anchor on prediction markets.** If liquid market prices (Polymarket / Kalshi) or a community forecast appear in the evidence, treat them as a strong, well-calibrated prior. Your final estimate should rarely sit more than ~15 percentage points from a liquid market on the SAME question \u2014 move further only with specific evidence the market lacks.\n- **Treat research as fallible, not ground truth.** A single-source or \"very recent\" claim \u2014 especially one the evidence flags as unverified, possibly AI-generated, or low-credibility \u2014 must not drive you to near-certainty. When a load-bearing fact is unverified, keep at least 10-15% on the chance it is wrong.\n- **Also provide a holistic estimate** \u2014 your overall gut feeling about the main question, BEFORE you see the mathematical combination. This serves as a sanity check: if the Fermi result and holistic estimate diverge wildly, something is wrong.\n\n## Output\n\nReturn ONLY valid JSON, no markdown fences:\n\n{\n \"rationale\": \"\u003caddress (a) (b) (c) (d) above \u2014 5-8 sentences total\u003e\",\n \"sub_question_estimates\": {\n \"sq1\": \u003cfloat in [0.01, 0.99]\u003e,\n \"sq2\": \u003cfloat in [0.01, 0.99]\u003e\n },\n \"holistic_p_yes\": \u003cfloat in [0.01, 0.99] \u2014 your overall estimate ignoring the decomposition\u003e,\n \"what_would_change_my_mind\": \"\u003c1-2 sentences: what new info would push you above 70% or below 30%\u003e\"\n}\n",
"holistic_p_yes": 0.38,
"models": [
"opus"
],
"p_yes": 0.39,
"rationale": "(a) About 8-9 months remain until the September 1, 2026 deadline. (b) Status quo: neither Anthropic nor Mistral is currently on the AI Pact signatories list; both skipped the initial September 2024 signing and neither has stated intent to join. (c) NO scenario: both firms conclude the AI Pact is redundant given they already signed the GPAI Code of Practice (a binding-ish, more substantive instrument), so they see little marginal value in a separate non-binding pledge and simply never sign. (d) YES scenario: Mistral, as a French/EU champion actively positioning itself as Europe\u0027s frontier lab, adds the AI Pact to its EU-alignment portfolio; or Anthropic, having already engaged via the GPAI Code, signs the low-cost voluntary pledge as a goodwill gesture. The GPAI Code signatures show both are willing to engage EU frameworks, which meaningfully raises the odds above pure status-quo inertia, but the AI Pact is a distinct instrument with over 230 signers that neither has joined despite the opportunity. Mistral\u0027s strong EU incentives make it the more likely of the two.",
"sub_question_estimates": {
"sq1": 0.15,
"sq2": 0.3
},
"what_would_change_my_mind": "A confirmed updated 2026 signatory list showing either firm added, or a public statement of intent by Mistral/Anthropic to join the AI Pact, would push me above 70%; explicit statements they consider it redundant with the GPAI Code would push me below 30%."
},
"plan": {
"combination_logic": "independent_or",
"domain": "tech",
"n_sub_qs": 2,
"n_tools": 3,
"reasoning_approach": "Each company represents an independent path to YES resolution (either signing suffices), so we forecast each separately and combine with independent_or. Research focuses on confirming current signatory status and any signals of intent to join the voluntary pledge.",
"sub_questions": [
{
"id": "sq1",
"question": "Will Anthropic appear on the EU AI Pact signatories list before September 1, 2026?",
"rationale": "Anthropic is a US-based frontier AI lab; its participation in the voluntary EU AI Pact is one of two independent paths to YES resolution.",
"weight": 0.5
},
{
"id": "sq2",
"question": "Will Mistral AI appear on the EU AI Pact signatories list before September 1, 2026?",
"rationale": "Mistral is a French AI company with strong EU ties and regulatory alignment incentives, making it plausibly more likely to sign an EU voluntary pledge.",
"weight": 0.5
}
],
"tool_requests": [
{
"parameters": {
"brief": "Determine whether Anthropic or Mistral AI have signed or are listed as signatories of the European Commission\u0027s EU AI Pact voluntary pledges. Check the official Commission signatories list and any announcements about these two companies joining.",
"max_searches": 4,
"question_title": "Will Anthropic or Mistral AI sign the European Commission\u0027s AI Pact before September 1, 2026?"
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "claude_news"
},
{
"parameters": {
"queries": [
"EU AI Pact signatories list Anthropic Mistral",
"Mistral AI EU AI Pact pledge signed",
"Anthropic AI Pact European Commission voluntary pledge"
]
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "web_search"
},
{
"parameters": {
"lookback_days": 180,
"queries": [
"AI Pact signatories European Commission new companies",
"Mistral AI EU AI Act compliance pledge",
"Anthropic Europe regulatory commitment AI Pact"
]
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "article_search"
}
]
},
"question": {
"close_time": "2026-07-10T12:00:00Z",
"description": "## Description\nAccording to the resolution source, \"The EU AI Pact voluntary pledges call on participating companies to commit to at least three core actions:\n\nAdopting an AI governance strategy to foster the uptake of AI in the organisation and work towards future compliance with the AI Act\nIdentifying and mapping AI systems likely to be categorised as high-risk under the AI Act\nPromoting AI awareness and literacy among staff, ensuring ethical and responsible AI development\"\n\n`{\"format\": \"bot_tournament_question\", \"info\": {\"hash_id\": \"3ea566f33105cc2b\", \"sheet_id\": \"92\"}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if, before September 1, 2026, Anthropic or Mistral AI appear at the AI Pact [Signatories of the pledges](https://digital-strategy.ec.europa.eu/en/policies/ai-pact#ecl-inpage-Signatories-of-the-AI-Pact) list maintained by the European Commission.",
"question_type": "binary",
"title": "Will Anthropic or Mistral AI sign the European Commission\u0027s AI Pact before September 1, 2026?"
},
"research": {
"cross_market_brief": "## Cross-Market Signals\n\n### No signal found",
"errors": [],
"has_cross_market": true,
"n_errors": 0,
"n_tools": 3,
"tools": [
{
"elapsed_s": 30.41,
"error": null,
"success": true,
"summary": "11 citations",
"tool_name": "claude_news"
},
{
"elapsed_s": 42.99,
"error": null,
"success": true,
"summary": "0 results",
"tool_name": "web_search"
},
{
"elapsed_s": 0.68,
"error": null,
"success": true,
"summary": "29 articles",
"tool_name": "article_search"
}
]
},
"synthesis": {
"evidence": [
{
"claim": "Anthropic was not among the 115 initial EU AI Pact signatories in September 2024 and did not sign.",
"credibility": 85,
"direction": "DOWN",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "STRONG",
"sub_question_id": "sq1"
},
{
"claim": "Over 230 companies have since signed the AI Pact pledges, but Anthropic is not confirmed among the current signatories.",
"credibility": 70,
"direction": "NEUTRAL",
"priced_in": true,
"recency": "RECENT",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "Anthropic did sign the separate EU GPAI Code of Practice (July 2025), showing willingness to engage with EU AI regulatory frameworks.",
"credibility": 80,
"direction": "UP",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "Mistral AI was not among the initial EU AI Pact signatories in September 2024.",
"credibility": 85,
"direction": "DOWN",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "STRONG",
"sub_question_id": "sq2"
},
{
"claim": "Mistral AI signed the EU GPAI Code of Practice among the first signatories (July 2025) with no chapter limitation.",
"credibility": 80,
"direction": "UP",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq2"
},
{
"claim": "Mistral CEO Mensch frames Europe/AI as a strategic asset and positions Mistral as Europe\u0027s frontier lab, aligned with EU priorities.",
"credibility": 65,
"direction": "UP",
"priced_in": true,
"recency": "RECENT",
"source": "article_search",
"strength": "WEAK",
"sub_question_id": "sq2"
},
{
"claim": "Mistral is expanding EU infrastructure (Sweden data centers, $830M debt financing) emphasizing European AI autonomy.",
"credibility": 70,
"direction": "NEUTRAL",
"priced_in": true,
"recency": "RECENT",
"source": "article_search",
"strength": "WEAK",
"sub_question_id": "sq2"
},
{
"claim": "The AI Pact and GPAI Code of Practice are distinct instruments; GPAI signing does not automatically place a company on the AI Pact list.",
"credibility": 85,
"direction": "DOWN",
"priced_in": false,
"recency": "RECENT",
"source": "web_search",
"strength": "STRONG",
"sub_question_id": "sq1"
}
],
"information_gaps": [
"No confirmed current (2026) AI Pact signatory list showing/excluding Anthropic or Mistral",
"No stated intent by either firm to join AI Pact specifically",
"Base rate for late-joiners adding to the AI Pact list over time",
"Whether GPAI signatories tend to also sign the AI Pact"
],
"key_uncertainties": [
"Whether either firm sees value in AI Pact given they already signed GPAI Code",
"Timing of any signature relative to Sept 1, 2026 deadline",
"Anthropic\u0027s overall strategic reluctance to non-binding EU pledges",
"Mistral\u0027s EU-alignment incentives potentially driving a signature"
],
"n_evidence": 8
},
"timings": {
"forecast": 14.28,
"plan": 10.66,
"research": 42.99,
"synthesis": 15.35
}
}