Estimate the historical base rate of computer-related CPSC recalls per two-month period (Poisson model), adjust for recent enforcement momentum, then discount slightly for category-matching uncertainty in the portal search, blending these into a weighted average.
## Cross-Market Signals ### Polymarket - "Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?" → Yes: 0.00, Volume: $6.3M - "Will there be no change in Fed interest rates after the July 2026 meeting?" → Yes: 0.80, Volume: $6.0M
1. [sq1 | code_execution | MODERATE cred 55 | UP | VERY_RECENT] Poisson model estimates P(>=1 computer recall in a two-month window) ranges from 0.49 (4/yr) to 0.81 (10/yr). 2. [sq1 | web_search | STRONG cred 95 | UP | DATED] CPSC published a computer power supply recall on April 16, 2026, confirming the category is actively used. 3. [sq2 | web_search | MODERATE cred 80 | UP | DATED] At least one computer-related recall occurred in early 2026 (April), indicating ongoing recall activity. 4. [sq2 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No historical annual computer-recall count or trend data was surfaced to establish the true base rate. 5. [sq3 | web_search | MODERATE cred 60 | UP | DATED] The April 2026 recall was categorized as a computer power supply, suggesting portal search captures such items. 6. [sq3 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No direct evidence on whether SaferProducts 'computers' category tagging has classification or timing gaps. ## Cross-Market Signals ### Polymarket - "Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?" → Yes: 0.00, Volume: $6.3M - "Will there be no change in Fed interest rates after the July 2026 meeting?" → Yes: 0.80, Volume: $6.0M Information gaps: - Historical annual/two-month base rate of CPSC computer recalls not found - How SaferProducts 'computers' filter classifies recalls (accessories, PSUs, laptops) - Recall counts across 2023-2025 to validate Poisson assumptions - Any pending or announced computer recalls near July-August 2026 Key uncertainties: - True annual rate of computer-category recalls - Whether portal category tagging matches admin search terms - Whether recall pace is stable, rising, or falling in 2026
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 the CPSC publish any computer-related recalls in July or August 2026?
## Description / Resolution Criteria
## Description
At the time of this question, the most recent such recall is of [Manik and Apex-branded ATX Computer Power Supplies](https://www.cpsc.gov/Recalls/2026/Apex-Gaming-PCs-Recalls-Manik-and-Apex-branded-ATX-Computer-Power-Supplies-Due-to-Risk-of-Serious-Injury-or-Death-from-Electrical-Shock-and-Electrocution-Hazards) dated April 16, 2026.
`{"format": "bot_tournament_question", "info": {"hash_id": "790b95676b6d0b51", "sheet_id": "71"}}`
## Resolution Criteria
This question resolves as **Yes** if a search, conducted by a Metaculus admin on or after September 1, 2026, at the US Consumer Product Safety Commission's [SaferProducts portal](https://www.saferproducts.gov/PublicSearch) for "Recalls / Repairs" of "computers" returns any matches for the time period from July 1, 2026 to August 31, 2026.
## Sub-question decomposition
- (w=0.60) Does the CPSC historically publish at least one computer-related recall in any given two-month window? — The base rate of computer-related recalls per two-month period is the primary driver; CPSC issues recalls regularly acro
- (w=0.25) Is the recent pace of computer/electronics recalls (early 2026) consistent with or above historical norms? — Recent momentum (e.g., April 2026 power supply recall) indicates active enforcement in this category, raising the chance
- (w=0.15) Will the SaferProducts 'computers' category search specifically capture any Jul-Aug 2026 recall (no classification/timing gaps)? — Resolution depends on the specific portal search category matching; broad electronics recalls may or may not be tagged a
Combination rule: **weighted_average**
## Synthesized evidence
1. [sq1 | code_execution | MODERATE cred 55 | UP | VERY_RECENT] Poisson model estimates P(>=1 computer recall in a two-month window) ranges from 0.49 (4/yr) to 0.81 (10/yr).
2. [sq1 | web_search | STRONG cred 95 | UP | DATED] CPSC published a computer power supply recall on April 16, 2026, confirming the category is actively used.
3. [sq2 | web_search | MODERATE cred 80 | UP | DATED] At least one computer-related recall occurred in early 2026 (April), indicating ongoing recall activity.
4. [sq2 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No historical annual computer-recall count or trend data was surfaced to establish the true base rate.
5. [sq3 | web_search | MODERATE cred 60 | UP | DATED] The April 2026 recall was categorized as a computer power supply, suggesting portal search captures such items.
6. [sq3 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No direct evidence on whether SaferProducts 'computers' category tagging has classification or timing gaps.
## Cross-Market Signals
### Polymarket
- "Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?" → Yes: 0.00, Volume: $6.3M
- "Will there be no change in Fed interest rates after the July 2026 meeting?" → Yes: 0.80, Volume: $6.0M
Information gaps:
- Historical annual/two-month base rate of CPSC computer recalls not found
- How SaferProducts 'computers' filter classifies recalls (accessories, PSUs, laptops)
- Recall counts across 2023-2025 to validate Poisson assumptions
- Any pending or announced computer recalls near July-August 2026
Key uncertainties:
- True annual rate of computer-category recalls
- Whether portal category tagging matches admin search terms
- Whether recall pace is stable, rising, or falling in 2026
## 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]>,
"sq3": <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": "weighted_average",
"evidence_brief": "1. [sq1 | code_execution | MODERATE cred 55 | UP | VERY_RECENT] Poisson model estimates P(\u003e=1 computer recall in a two-month window) ranges from 0.49 (4/yr) to 0.81 (10/yr).\n2. [sq1 | web_search | STRONG cred 95 | UP | DATED] CPSC published a computer power supply recall on April 16, 2026, confirming the category is actively used.\n3. [sq2 | web_search | MODERATE cred 80 | UP | DATED] At least one computer-related recall occurred in early 2026 (April), indicating ongoing recall activity.\n4. [sq2 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No historical annual computer-recall count or trend data was surfaced to establish the true base rate.\n5. [sq3 | web_search | MODERATE cred 60 | UP | DATED] The April 2026 recall was categorized as a computer power supply, suggesting portal search captures such items.\n6. [sq3 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No direct evidence on whether SaferProducts \u0027computers\u0027 category tagging has classification or timing gaps.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?\" \u2192 Yes: 0.00, Volume: $6.3M\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.80, Volume: $6.0M\n\nInformation gaps:\n - Historical annual/two-month base rate of CPSC computer recalls not found\n - How SaferProducts \u0027computers\u0027 filter classifies recalls (accessories, PSUs, laptops)\n - Recall counts across 2023-2025 to validate Poisson assumptions\n - Any pending or announced computer recalls near July-August 2026\n\nKey uncertainties:\n - True annual rate of computer-category recalls\n - Whether portal category tagging matches admin search terms\n - Whether recall pace is stable, rising, or falling in 2026",
"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 the CPSC publish any computer-related recalls in July or August 2026?\n\n## Description / Resolution Criteria\n## Description\nAt the time of this question, the most recent such recall is of [Manik and Apex-branded ATX Computer Power Supplies](https://www.cpsc.gov/Recalls/2026/Apex-Gaming-PCs-Recalls-Manik-and-Apex-branded-ATX-Computer-Power-Supplies-Due-to-Risk-of-Serious-Injury-or-Death-from-Electrical-Shock-and-Electrocution-Hazards) dated April 16, 2026.\n\n`{\"format\": \"bot_tournament_question\", \"info\": {\"hash_id\": \"790b95676b6d0b51\", \"sheet_id\": \"71\"}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if a search, conducted by a Metaculus admin on or after September 1, 2026, at the US Consumer Product Safety Commission\u0027s [SaferProducts portal](https://www.saferproducts.gov/PublicSearch) for \"Recalls / Repairs\" of \"computers\" returns any matches for the time period from July 1, 2026 to August 31, 2026.\n\n## Sub-question decomposition\n- (w=0.60) Does the CPSC historically publish at least one computer-related recall in any given two-month window? \u2014 The base rate of computer-related recalls per two-month period is the primary driver; CPSC issues recalls regularly acro\n- (w=0.25) Is the recent pace of computer/electronics recalls (early 2026) consistent with or above historical norms? \u2014 Recent momentum (e.g., April 2026 power supply recall) indicates active enforcement in this category, raising the chance\n- (w=0.15) Will the SaferProducts \u0027computers\u0027 category search specifically capture any Jul-Aug 2026 recall (no classification/timing gaps)? \u2014 Resolution depends on the specific portal search category matching; broad electronics recalls may or may not be tagged a\n\nCombination rule: **weighted_average**\n\n## Synthesized evidence\n1. [sq1 | code_execution | MODERATE cred 55 | UP | VERY_RECENT] Poisson model estimates P(\u003e=1 computer recall in a two-month window) ranges from 0.49 (4/yr) to 0.81 (10/yr).\n2. [sq1 | web_search | STRONG cred 95 | UP | DATED] CPSC published a computer power supply recall on April 16, 2026, confirming the category is actively used.\n3. [sq2 | web_search | MODERATE cred 80 | UP | DATED] At least one computer-related recall occurred in early 2026 (April), indicating ongoing recall activity.\n4. [sq2 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No historical annual computer-recall count or trend data was surfaced to establish the true base rate.\n5. [sq3 | web_search | MODERATE cred 60 | UP | DATED] The April 2026 recall was categorized as a computer power supply, suggesting portal search captures such items.\n6. [sq3 | web_search | WEAK cred 30 | NEUTRAL | VERY_RECENT] No direct evidence on whether SaferProducts \u0027computers\u0027 category tagging has classification or timing gaps.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?\" \u2192 Yes: 0.00, Volume: $6.3M\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.80, Volume: $6.0M\n\nInformation gaps:\n - Historical annual/two-month base rate of CPSC computer recalls not found\n - How SaferProducts \u0027computers\u0027 filter classifies recalls (accessories, PSUs, laptops)\n - Recall counts across 2023-2025 to validate Poisson assumptions\n - Any pending or announced computer recalls near July-August 2026\n\nKey uncertainties:\n - True annual rate of computer-category recalls\n - Whether portal category tagging matches admin search terms\n - Whether recall pace is stable, rising, or falling in 2026\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 \"sq3\": \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": 0.68,
"models": [
"opus"
],
"p_yes": 0.6905,
"rationale": "(a) The question resolves after September 1, 2026, roughly 4-5 months out from the April 2026 reference point. (b) Status quo: CPSC regularly publishes recalls including a recent computer power supply recall in April 2026, so an active category continues issuing recalls. (c) NO scenario: The specific \u0027computers\u0027 category search returns zero hits for Jul-Aug 2026 because recalls cluster elsewhere, or a broad electronics recall gets tagged under a different category, or simply no computer recall happens to fall in that particular two-month window (which is plausible given a moderate annual rate). (d) YES scenario: With computer recalls occurring at several per year and active enforcement momentum in 2026, at least one recall lands in the July-August window and is correctly tagged as \u0027computers.\u0027 The Poisson base rate (0.49-0.81) is the primary uncertainty, so I anchor sq1 around 0.65.",
"sub_question_estimates": {
"sq1": 0.65,
"sq2": 0.75,
"sq3": 0.8
},
"what_would_change_my_mind": "Historical counts showing computer recalls occur reliably (\u003e8/year) would push above 70%; evidence that the \u0027computers\u0027 filter frequently misses or that recalls are sparse (\u003c4/year) would push below 30%."
},
"plan": {
"combination_logic": "weighted_average",
"domain": "tech",
"n_sub_qs": 3,
"n_tools": 3,
"reasoning_approach": "Estimate the historical base rate of computer-related CPSC recalls per two-month period (Poisson model), adjust for recent enforcement momentum, then discount slightly for category-matching uncertainty in the portal search, blending these into a weighted average.",
"sub_questions": [
{
"id": "sq1",
"question": "Does the CPSC historically publish at least one computer-related recall in any given two-month window?",
"rationale": "The base rate of computer-related recalls per two-month period is the primary driver; CPSC issues recalls regularly across product categories.",
"weight": 0.6
},
{
"id": "sq2",
"question": "Is the recent pace of computer/electronics recalls (early 2026) consistent with or above historical norms?",
"rationale": "Recent momentum (e.g., April 2026 power supply recall) indicates active enforcement in this category, raising the chance of another in Jul-Aug.",
"weight": 0.25
},
{
"id": "sq3",
"question": "Will the SaferProducts \u0027computers\u0027 category search specifically capture any Jul-Aug 2026 recall (no classification/timing gaps)?",
"rationale": "Resolution depends on the specific portal search category matching; broad electronics recalls may or may not be tagged as \u0027computers\u0027.",
"weight": 0.15
}
],
"tool_requests": [
{
"parameters": {
"queries": [
"CPSC computer recall 2026",
"site:cpsc.gov recall computer power supply laptop 2026",
"SaferProducts recall computers 2025 2026"
]
},
"target_sub_questions": [
"sq1",
"sq2",
"sq3"
],
"tool_name": "web_search"
},
{
"parameters": {
"brief": "Determine how frequently the US CPSC publishes computer-related recalls (laptops, desktops, power supplies, batteries in computers) per two-month period historically, and how many have occurred in 2025 and early 2026. Assess base rate for at least one such recall in a given July-August window.",
"max_searches": 4,
"question_title": "Will the CPSC publish any computer-related recalls in July or August 2026?"
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "claude_news"
},
{
"parameters": {
"code": "import numpy as np\n# Estimate probability of \u003e=1 computer recall in a 2-month window given historical rate\n# Suppose historical data suggests ~4-8 computer-related recalls per year\nfor annual in [4,6,8,10]:\n rate_2mo = annual/6.0\n p_atleast1 = 1 - np.exp(-rate_2mo)\n print(f\u0027annual={annual}, 2mo_rate={rate_2mo:.2f}, P(\u003e=1)={p_atleast1:.3f}\u0027)",
"description": "Poisson base-rate estimate for at least one computer recall in a two-month window across plausible annual recall counts."
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "code_execution"
}
]
},
"question": {
"close_time": "2026-07-02T00:00:00Z",
"description": "## Description\nAt the time of this question, the most recent such recall is of [Manik and Apex-branded ATX Computer Power Supplies](https://www.cpsc.gov/Recalls/2026/Apex-Gaming-PCs-Recalls-Manik-and-Apex-branded-ATX-Computer-Power-Supplies-Due-to-Risk-of-Serious-Injury-or-Death-from-Electrical-Shock-and-Electrocution-Hazards) dated April 16, 2026.\n\n`{\"format\": \"bot_tournament_question\", \"info\": {\"hash_id\": \"790b95676b6d0b51\", \"sheet_id\": \"71\"}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if a search, conducted by a Metaculus admin on or after September 1, 2026, at the US Consumer Product Safety Commission\u0027s [SaferProducts portal](https://www.saferproducts.gov/PublicSearch) for \"Recalls / Repairs\" of \"computers\" returns any matches for the time period from July 1, 2026 to August 31, 2026.",
"question_type": "binary",
"title": "Will the CPSC publish any computer-related recalls in July or August 2026?"
},
"research": {
"cross_market_brief": "## Cross-Market Signals\n\n### Polymarket\n- \"Will the Fed decrease interest rates by 50+ bps after the July 2026 meeting?\" \u2192 Yes: 0.00, Volume: $6.3M\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.80, Volume: $6.0M",
"errors": [],
"has_cross_market": true,
"n_errors": 0,
"n_tools": 3,
"tools": [
{
"elapsed_s": 66.95,
"error": null,
"success": true,
"summary": "0 results",
"tool_name": "web_search"
},
{
"elapsed_s": 34.57,
"error": null,
"success": true,
"summary": "15 citations",
"tool_name": "claude_news"
},
{
"elapsed_s": 0.11,
"error": null,
"success": true,
"summary": "Poisson base-rate estimate for at least one computer recall ",
"tool_name": "code_execution"
}
]
},
"synthesis": {
"evidence": [
{
"claim": "Poisson model estimates P(\u003e=1 computer recall in a two-month window) ranges from 0.49 (4/yr) to 0.81 (10/yr).",
"credibility": 55,
"direction": "UP",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "code_execution",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "CPSC published a computer power supply recall on April 16, 2026, confirming the category is actively used.",
"credibility": 95,
"direction": "UP",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "STRONG",
"sub_question_id": "sq1"
},
{
"claim": "At least one computer-related recall occurred in early 2026 (April), indicating ongoing recall activity.",
"credibility": 80,
"direction": "UP",
"priced_in": true,
"recency": "DATED",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq2"
},
{
"claim": "No historical annual computer-recall count or trend data was surfaced to establish the true base rate.",
"credibility": 30,
"direction": "NEUTRAL",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "web_search",
"strength": "WEAK",
"sub_question_id": "sq2"
},
{
"claim": "The April 2026 recall was categorized as a computer power supply, suggesting portal search captures such items.",
"credibility": 60,
"direction": "UP",
"priced_in": false,
"recency": "DATED",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq3"
},
{
"claim": "No direct evidence on whether SaferProducts \u0027computers\u0027 category tagging has classification or timing gaps.",
"credibility": 30,
"direction": "NEUTRAL",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "web_search",
"strength": "WEAK",
"sub_question_id": "sq3"
}
],
"information_gaps": [
"Historical annual/two-month base rate of CPSC computer recalls not found",
"How SaferProducts \u0027computers\u0027 filter classifies recalls (accessories, PSUs, laptops)",
"Recall counts across 2023-2025 to validate Poisson assumptions",
"Any pending or announced computer recalls near July-August 2026"
],
"key_uncertainties": [
"True annual rate of computer-category recalls",
"Whether portal category tagging matches admin search terms",
"Whether recall pace is stable, rising, or falling in 2026"
],
"n_evidence": 6
},
"timings": {
"forecast": 12.77,
"plan": 20.18,
"research": 66.95,
"synthesis": 12.0
}
}