Estimate the epidemic curve's shape from the latest MDHHS weekly updates (whether cases are still accelerating or have peaked), then translate plateau case totals times a hospitalization rate into a distribution for cumulative hospitalizations by Aug 31; the weighted average of the deceleration, end-of-July threshold, and severity-ratio sub-questions gives the final probability.
## Cross-Market Signals ### Polymarket - "Will Trump meet with Netanyahu by August 31, 2026?" → Yes: 0.95, Volume: $148.1K - "Kharg Island no longer under Iranian control by August 31?" → Yes: 0.09, Volume: $2.5M
1. [sq2 | article_search | STRONG cred 93 | DOWN | VERY_RECENT] MDHHS reported 160 cumulative hospitalizations as of July 23, up from 102 on July 16 and 44 on July 9. 2. [sq2 | article_search | STRONG cred 90 | DOWN | VERY_RECENT] Weekly hospitalization increments were +58 in each of the last two weekly updates (44→102→160), i.e., a roughly linear pace. 3. [sq1 | article_search | STRONG cred 92 | DOWN | VERY_RECENT] Michigan cases rose from 4,312 (July 16) to 8,176 (July 24), including daily jumps of ~500, showing no deceleration in reported cases. 4. [sq3 | article_search | MODERATE cred 85 | UP | VERY_RECENT] Hospitalization-to-case ratio in Michigan is about 2.1% (160/7,664) as of July 23, down from 2.4% on July 16. 5. [sq1 | article_search | MODERATE cred 80 | UP | VERY_RECENT] Taylor Farms lettuce was recalled amid the national Cyclospora outbreak, with a New Hampshire cluster confirmed linked; recalled product removed from service by July 20. 6. [sq1 | web_search | MODERATE cred 82 | DOWN | VERY_RECENT] CDC states illness onset dates in the multistate Taco Bell-linked cluster have continued through July 20, 2026. 7. [sq3 | web_search | MODERATE cred 85 | NEUTRAL | VERY_RECENT] CDC reported 4,173 confirmed domestically acquired cases nationally with 308 hospitalizations (~7%) as of July 21, using confirmed-only case definitions. 8. [sq2 | article_search | STRONG cred 90 | NEUTRAL | VERY_RECENT] MDHHS updates hospitalization counts only weekly on Thursdays, meaning roughly five more updates fall before August 31, 2026. 9. [sq3 | article_search | MODERATE cred 88 | UP | RECENT] Cyclosporiasis is described as not usually life-threatening and treatable with antibiotics; no deaths reported in the 2026 outbreak. 10. [sq1 | article_search | MODERATE cred 88 | NEUTRAL | RECENT] MDHHS identified lettuce/salad greens as the likely source on July 13-14 but had not named a specific grower or supplier at that time. 11. [sq1 | article_search | MODERATE cred 85 | DOWN | VERY_RECENT] Michigan's outbreak spread to 71 of 83 counties by July 24 and is called the worst documented US parasitic foodborne event; state normally sees ~50 cases/year. 12. [sq2 | article_search | WEAK cred 80 | NEUTRAL | VERY_RECENT] Neighboring states show much lower burdens (Illinois 408 cases/31 hospitalizations; Ohio 361 cases/46 hospitalizations), indicating Michigan's outbreak is the dominant cluster. ## Cross-Market Signals ### Polymarket - "Will Trump meet with Netanyahu by August 31, 2026?" → Yes: 0.95, Volume: $148.1K - "Kharg Island no longer under Iranian control by August 31?" → Yes: 0.09, Volume: $2.5M Information gaps: - No epidemic-curve data by symptom-onset date (only report date), so true peak timing unknown - No base rates for how quickly past large cyclospora/produce outbreaks decayed after recall - No data on reporting lag between hospitalization and MDHHS inclusion, or retrospective backfill practice - No MDHHS update after July 24; no Kalshi/market pricing provided Key uncertainties: - Whether the July 20 Taylor Farms recall halted new exposures promptly - Whether weekly hospitalization increments stay near +58 or decay quickly - Whether MDHHS revises/backfills hospitalization counts upward - Plateau case total (12,000+ at ~2% would breach 300)
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 total number of hospitalizations from cyclosporiasis in Michigan remain under 300 through the end of August 2026?
## Description / Resolution Criteria
## Description
CBS News: [Michigan cyclosporiasis case numbers top 4,300, state health officials say](https://www.cbsnews.com/detroit/news/michigan-cyclosporiasis-outbreak-cases-july-16/)
> The number of reported cases, counting from the first known in this outbreak on June 22, was 4,312 as of July 16. The number was 3,762 on July 15.
> Health officials also say 102 people had been hospitalized in the outbreak as of July 16. That's more than double the previous weekly count, which was 44 people who had hospital care as of July 9.
> Cyclospora cayetanensis is a parasite that causes the diarrheal illness cyclosporiasis. The Centers for Disease Control and Prevention says the most common symptoms associated with the illness are frequent watery diarrhea, loss of appetite, bloating, nausea and fatigue. Some people may also experience body aches, headache or vomiting.
`{"format": "metac_reveal_and_close_in_period", "info": {"post_id": 44683, "question_id": 44838}}`
## Resolution Criteria
This question resolves as **Yes** if, according to the [Michigan Department of Health & Human Services](https://www.michigan.gov/mdhhs/keep-mi-healthy/infectious-diseases/infectious-disease-outbreaks), the number of hospitalized cyclosporiasis cases from the 2026 outbreak remains under 300 through August 31, 2026. 
## Fine Print
This question's information (resolution criteria, fine print, background info, etc) is synced with an [original identical question](https://www.metaculus.com/questions/44683) which opened on 2026-07-17 12:00:00. This question will resolve based on the resolution criteria and fine print of the linked original question. However, if this question would resolve differently than the original question, then this question will be annulled. Additionally, if the original question's resolution could have been known before this question opened, then this question will be annulled.
## Sub-question decomposition
- (w=0.30) Will the Michigan cyclosporiasis outbreak's weekly new-case counts clearly decelerate (fewer new cases reported in the week ending ~July 29, 2026 than in the week ending July 16, 2026), indicating the exposure source has been removed? — Hospitalizations track total cases; if the epidemic curve peaks in mid-to-late July, cumulative hospitalizations plateau
- (w=0.40) Will MDHHS-reported cumulative hospitalizations remain under 200 as of the final July 2026 weekly update (~July 29-31)? — Given 102 on July 16, staying under 200 by end of July is the key checkpoint; crossing 200 in July would make 300 by Aug
- (w=0.30) Will the ratio of hospitalizations to reported cases stay at or below roughly 3% as the outbreak's case total plateaus (i.e., no upward revision in severity or large retrospective backfill of hospitalizations)? — Hospitalization reporting lags and case-investigation backfill can push cumulative counts up sharply even after cases st
Combination rule: **weighted_average**
## Synthesized evidence
1. [sq2 | article_search | STRONG cred 93 | DOWN | VERY_RECENT] MDHHS reported 160 cumulative hospitalizations as of July 23, up from 102 on July 16 and 44 on July 9.
2. [sq2 | article_search | STRONG cred 90 | DOWN | VERY_RECENT] Weekly hospitalization increments were +58 in each of the last two weekly updates (44→102→160), i.e., a roughly linear pace.
3. [sq1 | article_search | STRONG cred 92 | DOWN | VERY_RECENT] Michigan cases rose from 4,312 (July 16) to 8,176 (July 24), including daily jumps of ~500, showing no deceleration in reported cases.
4. [sq3 | article_search | MODERATE cred 85 | UP | VERY_RECENT] Hospitalization-to-case ratio in Michigan is about 2.1% (160/7,664) as of July 23, down from 2.4% on July 16.
5. [sq1 | article_search | MODERATE cred 80 | UP | VERY_RECENT] Taylor Farms lettuce was recalled amid the national Cyclospora outbreak, with a New Hampshire cluster confirmed linked; recalled product removed from service by July 20.
6. [sq1 | web_search | MODERATE cred 82 | DOWN | VERY_RECENT] CDC states illness onset dates in the multistate Taco Bell-linked cluster have continued through July 20, 2026.
7. [sq3 | web_search | MODERATE cred 85 | NEUTRAL | VERY_RECENT] CDC reported 4,173 confirmed domestically acquired cases nationally with 308 hospitalizations (~7%) as of July 21, using confirmed-only case definitions.
8. [sq2 | article_search | STRONG cred 90 | NEUTRAL | VERY_RECENT] MDHHS updates hospitalization counts only weekly on Thursdays, meaning roughly five more updates fall before August 31, 2026.
9. [sq3 | article_search | MODERATE cred 88 | UP | RECENT] Cyclosporiasis is described as not usually life-threatening and treatable with antibiotics; no deaths reported in the 2026 outbreak.
10. [sq1 | article_search | MODERATE cred 88 | NEUTRAL | RECENT] MDHHS identified lettuce/salad greens as the likely source on July 13-14 but had not named a specific grower or supplier at that time.
11. [sq1 | article_search | MODERATE cred 85 | DOWN | VERY_RECENT] Michigan's outbreak spread to 71 of 83 counties by July 24 and is called the worst documented US parasitic foodborne event; state normally sees ~50 cases/year.
12. [sq2 | article_search | WEAK cred 80 | NEUTRAL | VERY_RECENT] Neighboring states show much lower burdens (Illinois 408 cases/31 hospitalizations; Ohio 361 cases/46 hospitalizations), indicating Michigan's outbreak is the dominant cluster.
## Cross-Market Signals
### Polymarket
- "Will Trump meet with Netanyahu by August 31, 2026?" → Yes: 0.95, Volume: $148.1K
- "Kharg Island no longer under Iranian control by August 31?" → Yes: 0.09, Volume: $2.5M
Information gaps:
- No epidemic-curve data by symptom-onset date (only report date), so true peak timing unknown
- No base rates for how quickly past large cyclospora/produce outbreaks decayed after recall
- No data on reporting lag between hospitalization and MDHHS inclusion, or retrospective backfill practice
- No MDHHS update after July 24; no Kalshi/market pricing provided
Key uncertainties:
- Whether the July 20 Taylor Farms recall halted new exposures promptly
- Whether weekly hospitalization increments stay near +58 or decay quickly
- Whether MDHHS revises/backfills hospitalization counts upward
- Plateau case total (12,000+ at ~2% would breach 300)
## 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. [sq2 | article_search | STRONG cred 93 | DOWN | VERY_RECENT] MDHHS reported 160 cumulative hospitalizations as of July 23, up from 102 on July 16 and 44 on July 9.\n2. [sq2 | article_search | STRONG cred 90 | DOWN | VERY_RECENT] Weekly hospitalization increments were +58 in each of the last two weekly updates (44\u2192102\u2192160), i.e., a roughly linear pace.\n3. [sq1 | article_search | STRONG cred 92 | DOWN | VERY_RECENT] Michigan cases rose from 4,312 (July 16) to 8,176 (July 24), including daily jumps of ~500, showing no deceleration in reported cases.\n4. [sq3 | article_search | MODERATE cred 85 | UP | VERY_RECENT] Hospitalization-to-case ratio in Michigan is about 2.1% (160/7,664) as of July 23, down from 2.4% on July 16.\n5. [sq1 | article_search | MODERATE cred 80 | UP | VERY_RECENT] Taylor Farms lettuce was recalled amid the national Cyclospora outbreak, with a New Hampshire cluster confirmed linked; recalled product removed from service by July 20.\n6. [sq1 | web_search | MODERATE cred 82 | DOWN | VERY_RECENT] CDC states illness onset dates in the multistate Taco Bell-linked cluster have continued through July 20, 2026.\n7. [sq3 | web_search | MODERATE cred 85 | NEUTRAL | VERY_RECENT] CDC reported 4,173 confirmed domestically acquired cases nationally with 308 hospitalizations (~7%) as of July 21, using confirmed-only case definitions.\n8. [sq2 | article_search | STRONG cred 90 | NEUTRAL | VERY_RECENT] MDHHS updates hospitalization counts only weekly on Thursdays, meaning roughly five more updates fall before August 31, 2026.\n9. [sq3 | article_search | MODERATE cred 88 | UP | RECENT] Cyclosporiasis is described as not usually life-threatening and treatable with antibiotics; no deaths reported in the 2026 outbreak.\n10. [sq1 | article_search | MODERATE cred 88 | NEUTRAL | RECENT] MDHHS identified lettuce/salad greens as the likely source on July 13-14 but had not named a specific grower or supplier at that time.\n11. [sq1 | article_search | MODERATE cred 85 | DOWN | VERY_RECENT] Michigan\u0027s outbreak spread to 71 of 83 counties by July 24 and is called the worst documented US parasitic foodborne event; state normally sees ~50 cases/year.\n12. [sq2 | article_search | WEAK cred 80 | NEUTRAL | VERY_RECENT] Neighboring states show much lower burdens (Illinois 408 cases/31 hospitalizations; Ohio 361 cases/46 hospitalizations), indicating Michigan\u0027s outbreak is the dominant cluster.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will Trump meet with Netanyahu by August 31, 2026?\" \u2192 Yes: 0.95, Volume: $148.1K\n- \"Kharg Island no longer under Iranian control by August 31?\" \u2192 Yes: 0.09, Volume: $2.5M\n\nInformation gaps:\n - No epidemic-curve data by symptom-onset date (only report date), so true peak timing unknown\n - No base rates for how quickly past large cyclospora/produce outbreaks decayed after recall\n - No data on reporting lag between hospitalization and MDHHS inclusion, or retrospective backfill practice\n - No MDHHS update after July 24; no Kalshi/market pricing provided\n\nKey uncertainties:\n - Whether the July 20 Taylor Farms recall halted new exposures promptly\n - Whether weekly hospitalization increments stay near +58 or decay quickly\n - Whether MDHHS revises/backfills hospitalization counts upward\n - Plateau case total (12,000+ at ~2% would breach 300)",
"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 total number of hospitalizations from cyclosporiasis in Michigan remain under 300 through the end of August 2026?\n\n## Description / Resolution Criteria\n## Description\nCBS News: [Michigan cyclosporiasis case numbers top 4,300, state health officials say](https://www.cbsnews.com/detroit/news/michigan-cyclosporiasis-outbreak-cases-july-16/)\n\n\u003e The number of reported cases, counting from the first known in this outbreak on June 22, was 4,312 as of July 16. The number was 3,762 on July 15.\n\n\u003e Health officials also say 102 people had been hospitalized in the outbreak as of July 16. That\u0027s more than double the previous weekly count, which was 44 people who had hospital care as of July 9.\n\n\u003e Cyclospora cayetanensis is a parasite that causes the diarrheal illness cyclosporiasis. The Centers for Disease Control and Prevention says the most common symptoms associated with the illness are frequent watery diarrhea, loss of appetite, bloating, nausea and fatigue. Some people may also experience body aches, headache or vomiting.\n\n`{\"format\": \"metac_reveal_and_close_in_period\", \"info\": {\"post_id\": 44683, \"question_id\": 44838}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if, according to the [Michigan Department of Health \u0026 Human Services](https://www.michigan.gov/mdhhs/keep-mi-healthy/infectious-diseases/infectious-disease-outbreaks), the number of hospitalized cyclosporiasis cases from the 2026 outbreak remains under 300 through August 31, 2026.\u0026#x20;\n\n## Fine Print\nThis question\u0027s information (resolution criteria, fine print, background info, etc) is synced with an [original identical question](https://www.metaculus.com/questions/44683) which opened on 2026-07-17 12:00:00. This question will resolve based on the resolution criteria and fine print of the linked original question. However, if this question would resolve differently than the original question, then this question will be annulled. Additionally, if the original question\u0027s resolution could have been known before this question opened, then this question will be annulled.\n\n## Sub-question decomposition\n- (w=0.30) Will the Michigan cyclosporiasis outbreak\u0027s weekly new-case counts clearly decelerate (fewer new cases reported in the week ending ~July 29, 2026 than in the week ending July 16, 2026), indicating the exposure source has been removed? \u2014 Hospitalizations track total cases; if the epidemic curve peaks in mid-to-late July, cumulative hospitalizations plateau\n- (w=0.40) Will MDHHS-reported cumulative hospitalizations remain under 200 as of the final July 2026 weekly update (~July 29-31)? \u2014 Given 102 on July 16, staying under 200 by end of July is the key checkpoint; crossing 200 in July would make 300 by Aug\n- (w=0.30) Will the ratio of hospitalizations to reported cases stay at or below roughly 3% as the outbreak\u0027s case total plateaus (i.e., no upward revision in severity or large retrospective backfill of hospitalizations)? \u2014 Hospitalization reporting lags and case-investigation backfill can push cumulative counts up sharply even after cases st\n\nCombination rule: **weighted_average**\n\n## Synthesized evidence\n1. [sq2 | article_search | STRONG cred 93 | DOWN | VERY_RECENT] MDHHS reported 160 cumulative hospitalizations as of July 23, up from 102 on July 16 and 44 on July 9.\n2. [sq2 | article_search | STRONG cred 90 | DOWN | VERY_RECENT] Weekly hospitalization increments were +58 in each of the last two weekly updates (44\u2192102\u2192160), i.e., a roughly linear pace.\n3. [sq1 | article_search | STRONG cred 92 | DOWN | VERY_RECENT] Michigan cases rose from 4,312 (July 16) to 8,176 (July 24), including daily jumps of ~500, showing no deceleration in reported cases.\n4. [sq3 | article_search | MODERATE cred 85 | UP | VERY_RECENT] Hospitalization-to-case ratio in Michigan is about 2.1% (160/7,664) as of July 23, down from 2.4% on July 16.\n5. [sq1 | article_search | MODERATE cred 80 | UP | VERY_RECENT] Taylor Farms lettuce was recalled amid the national Cyclospora outbreak, with a New Hampshire cluster confirmed linked; recalled product removed from service by July 20.\n6. [sq1 | web_search | MODERATE cred 82 | DOWN | VERY_RECENT] CDC states illness onset dates in the multistate Taco Bell-linked cluster have continued through July 20, 2026.\n7. [sq3 | web_search | MODERATE cred 85 | NEUTRAL | VERY_RECENT] CDC reported 4,173 confirmed domestically acquired cases nationally with 308 hospitalizations (~7%) as of July 21, using confirmed-only case definitions.\n8. [sq2 | article_search | STRONG cred 90 | NEUTRAL | VERY_RECENT] MDHHS updates hospitalization counts only weekly on Thursdays, meaning roughly five more updates fall before August 31, 2026.\n9. [sq3 | article_search | MODERATE cred 88 | UP | RECENT] Cyclosporiasis is described as not usually life-threatening and treatable with antibiotics; no deaths reported in the 2026 outbreak.\n10. [sq1 | article_search | MODERATE cred 88 | NEUTRAL | RECENT] MDHHS identified lettuce/salad greens as the likely source on July 13-14 but had not named a specific grower or supplier at that time.\n11. [sq1 | article_search | MODERATE cred 85 | DOWN | VERY_RECENT] Michigan\u0027s outbreak spread to 71 of 83 counties by July 24 and is called the worst documented US parasitic foodborne event; state normally sees ~50 cases/year.\n12. [sq2 | article_search | WEAK cred 80 | NEUTRAL | VERY_RECENT] Neighboring states show much lower burdens (Illinois 408 cases/31 hospitalizations; Ohio 361 cases/46 hospitalizations), indicating Michigan\u0027s outbreak is the dominant cluster.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will Trump meet with Netanyahu by August 31, 2026?\" \u2192 Yes: 0.95, Volume: $148.1K\n- \"Kharg Island no longer under Iranian control by August 31?\" \u2192 Yes: 0.09, Volume: $2.5M\n\nInformation gaps:\n - No epidemic-curve data by symptom-onset date (only report date), so true peak timing unknown\n - No base rates for how quickly past large cyclospora/produce outbreaks decayed after recall\n - No data on reporting lag between hospitalization and MDHHS inclusion, or retrospective backfill practice\n - No MDHHS update after July 24; no Kalshi/market pricing provided\n\nKey uncertainties:\n - Whether the July 20 Taylor Farms recall halted new exposures promptly\n - Whether weekly hospitalization increments stay near +58 or decay quickly\n - Whether MDHHS revises/backfills hospitalization counts upward\n - Plateau case total (12,000+ at ~2% would breach 300)\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": 0.42,
"models": [
"opus"
],
"p_yes": 0.4344,
"rationale": "(a) About five more weekly MDHHS Thursday updates fall between the last known data point (160 hospitalizations, July 23, 2026) and the August 31, 2026 deadline. (b) Status quo: increments have been a linear +58/week (44\u2192102\u2192160) while cases exploded from 4,312 to 8,176 in eight days; simple extrapolation of that pace gives ~450 by August 31, i.e., NO. Only a fairly rapid decay (averaging \u003c28 new hospitalizations per week) keeps the total under 300. (c) NO scenario: reported cases keep pouring in through late July/early August as testing and awareness surge, the plateau case total reaches 15,000+ at a ~2% hospitalization ratio, or MDHHS backfills hospitalizations retrospectively \u2014 300 is breached in mid-to-late August. (d) YES scenario: the July 20 Taylor Farms lettuce recall truly ended exposures, so with a ~7-day incubation and ~1-2 week reporting lag, case reports peak around late July and decay sharply; the case plateau lands near 11,000-13,000 with a falling ratio (2.4%\u21922.1%\u2192~1.7% as mild cases are ascertained), yielding ~230-270 hospitalizations. The arithmetic sits almost exactly on the 300 threshold, so this is close to a coin flip with a modest tilt toward breaching, since a single week of continued +58 pace plus a slow tail consumes the entire remaining headroom of 140.",
"sub_question_estimates": {
"sq1": 0.42,
"sq2": 0.15,
"sq3": 0.86
},
"what_would_change_my_mind": "An MDHHS update showing weekly hospitalization increments collapsing (e.g., \u003c25 in the week ending July 30) and case reports clearly falling would push me above 70%; continued +50/week increments or a reported retrospective backfill/upward revision past ~230 by early August would push me below 20%."
},
"plan": {
"combination_logic": "weighted_average",
"domain": "health",
"n_sub_qs": 3,
"n_tools": 4,
"reasoning_approach": "Estimate the epidemic curve\u0027s shape from the latest MDHHS weekly updates (whether cases are still accelerating or have peaked), then translate plateau case totals times a hospitalization rate into a distribution for cumulative hospitalizations by Aug 31; the weighted average of the deceleration, end-of-July threshold, and severity-ratio sub-questions gives the final probability.",
"sub_questions": [
{
"id": "sq1",
"question": "Will the Michigan cyclosporiasis outbreak\u0027s weekly new-case counts clearly decelerate (fewer new cases reported in the week ending ~July 29, 2026 than in the week ending July 16, 2026), indicating the exposure source has been removed?",
"rationale": "Hospitalizations track total cases; if the epidemic curve peaks in mid-to-late July, cumulative hospitalizations plateau well below 300.",
"weight": 0.3
},
{
"id": "sq2",
"question": "Will MDHHS-reported cumulative hospitalizations remain under 200 as of the final July 2026 weekly update (~July 29-31)?",
"rationale": "Given 102 on July 16, staying under 200 by end of July is the key checkpoint; crossing 200 in July would make 300 by August 31 very likely.",
"weight": 0.4
},
{
"id": "sq3",
"question": "Will the ratio of hospitalizations to reported cases stay at or below roughly 3% as the outbreak\u0027s case total plateaus (i.e., no upward revision in severity or large retrospective backfill of hospitalizations)?",
"rationale": "Hospitalization reporting lags and case-investigation backfill can push cumulative counts up sharply even after cases stop; 102/4,312 \u2248 2.4%, so a plateau near 6,000-8,000 cases at ~2.5-3% would land near 150-240.",
"weight": 0.3
}
],
"tool_requests": [
{
"parameters": {
"brief": "Find the latest MDHHS (Michigan Department of Health \u0026 Human Services) weekly updates on the 2026 cyclosporiasis outbreak: cumulative case counts, cumulative hospitalization counts, dates of each weekly update, whether the source food/produce has been identified and recalled, and whether new cases are declining. Include any July 2026 news after July 16.",
"max_searches": 4,
"question_title": "Will total cyclosporiasis hospitalizations in Michigan remain under 300 through August 31, 2026?"
},
"target_sub_questions": [
"sq1",
"sq2",
"sq3"
],
"tool_name": "claude_news"
},
{
"parameters": {
"queries": [
"Michigan cyclosporiasis outbreak hospitalized cases MDHHS update",
"MDHHS cyclosporiasis outbreak 2026 case count hospitalizations July",
"Michigan cyclospora outbreak source identified recall"
]
},
"target_sub_questions": [
"sq1",
"sq2"
],
"tool_name": "web_search"
},
{
"parameters": {
"lookback_days": 45,
"queries": [
"Michigan cyclosporiasis outbreak hospitalizations",
"cyclospora Michigan cases decline peak",
"Michigan health department cyclosporiasis weekly update"
]
},
"target_sub_questions": [
"sq1",
"sq2",
"sq3"
],
"tool_name": "article_search"
},
{
"parameters": {
"code": "import numpy as np\n# Model cumulative hospitalizations by Aug 31 under scenarios\n# Known: hosp 44 (Jul 9), 102 (Jul 16); cases 3762 (Jul 15), 4312 (Jul 16)\nnp.random.seed(0)\nN=200000\n# scenario: cumulative cases plateau (logistic) with total final cases, hosp rate\nfinal_cases = np.random.lognormal(np.log(7000),0.45,N) # plateau total cases\nhosp_rate = np.random.lognormal(np.log(0.026),0.35,N) # hosp per case incl backfill\nhosp = final_cases*hosp_rate\nprint(\u0027P(\u003c300) plateau model\u0027, (hosp\u003c300).mean())\nprint(np.percentile(hosp,[10,25,50,75,90]))\n# alternative: continued exponential growth in hosp for k more weeks then stop\nfor wk in [1,2,3]:\n for g in [1.3,1.5,1.8,2.0]:\n print(wk,g,102*g**wk)\n",
"description": "Monte Carlo of final hospitalization count under plateau assumptions plus deterministic weekly-growth scenarios."
},
"target_sub_questions": [
"sq2",
"sq3"
],
"tool_name": "code_execution"
}
]
},
"question": {
"close_time": "2026-07-25T12:00:00Z",
"description": "## Description\nCBS News: [Michigan cyclosporiasis case numbers top 4,300, state health officials say](https://www.cbsnews.com/detroit/news/michigan-cyclosporiasis-outbreak-cases-july-16/)\n\n\u003e The number of reported cases, counting from the first known in this outbreak on June 22, was 4,312 as of July 16. The number was 3,762 on July 15.\n\n\u003e Health officials also say 102 people had been hospitalized in the outbreak as of July 16. That\u0027s more than double the previous weekly count, which was 44 people who had hospital care as of July 9.\n\n\u003e Cyclospora cayetanensis is a parasite that causes the diarrheal illness cyclosporiasis. The Centers for Disease Control and Prevention says the most common symptoms associated with the illness are frequent watery diarrhea, loss of appetite, bloating, nausea and fatigue. Some people may also experience body aches, headache or vomiting.\n\n`{\"format\": \"metac_reveal_and_close_in_period\", \"info\": {\"post_id\": 44683, \"question_id\": 44838}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** if, according to the [Michigan Department of Health \u0026 Human Services](https://www.michigan.gov/mdhhs/keep-mi-healthy/infectious-diseases/infectious-disease-outbreaks), the number of hospitalized cyclosporiasis cases from the 2026 outbreak remains under 300 through August 31, 2026.\u0026#x20;\n\n## Fine Print\nThis question\u0027s information (resolution criteria, fine print, background info, etc) is synced with an [original identical question](https://www.metaculus.com/questions/44683) which opened on 2026-07-17 12:00:00. This question will resolve based on the resolution criteria and fine print of the linked original question. However, if this question would resolve differently than the original question, then this question will be annulled. Additionally, if the original question\u0027s resolution could have been known before this question opened, then this question will be annulled.",
"question_type": "binary",
"title": "Will the total number of hospitalizations from cyclosporiasis in Michigan remain under 300 through the end of August 2026?"
},
"research": {
"cross_market_brief": "## Cross-Market Signals\n\n### Polymarket\n- \"Will Trump meet with Netanyahu by August 31, 2026?\" \u2192 Yes: 0.95, Volume: $148.1K\n- \"Kharg Island no longer under Iranian control by August 31?\" \u2192 Yes: 0.09, Volume: $2.5M",
"errors": [],
"has_cross_market": true,
"n_errors": 0,
"n_tools": 4,
"tools": [
{
"elapsed_s": 25.63,
"error": null,
"success": true,
"summary": "12 citations",
"tool_name": "claude_news"
},
{
"elapsed_s": 32.2,
"error": null,
"success": true,
"summary": "0 results",
"tool_name": "web_search"
},
{
"elapsed_s": 0.43,
"error": null,
"success": true,
"summary": "24 articles",
"tool_name": "article_search"
},
{
"elapsed_s": 0.17,
"error": null,
"success": true,
"summary": "Monte Carlo of final hospitalization count under plateau ass",
"tool_name": "code_execution"
}
]
},
"synthesis": {
"evidence": [
{
"claim": "MDHHS reported 160 cumulative hospitalizations as of July 23, up from 102 on July 16 and 44 on July 9.",
"credibility": 93,
"direction": "DOWN",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "STRONG",
"sub_question_id": "sq2"
},
{
"claim": "Weekly hospitalization increments were +58 in each of the last two weekly updates (44\u2192102\u2192160), i.e., a roughly linear pace.",
"credibility": 90,
"direction": "DOWN",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "STRONG",
"sub_question_id": "sq2"
},
{
"claim": "Michigan cases rose from 4,312 (July 16) to 8,176 (July 24), including daily jumps of ~500, showing no deceleration in reported cases.",
"credibility": 92,
"direction": "DOWN",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "STRONG",
"sub_question_id": "sq1"
},
{
"claim": "Hospitalization-to-case ratio in Michigan is about 2.1% (160/7,664) as of July 23, down from 2.4% on July 16.",
"credibility": 85,
"direction": "UP",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "MODERATE",
"sub_question_id": "sq3"
},
{
"claim": "Taylor Farms lettuce was recalled amid the national Cyclospora outbreak, with a New Hampshire cluster confirmed linked; recalled product removed from service by July 20.",
"credibility": 80,
"direction": "UP",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "CDC states illness onset dates in the multistate Taco Bell-linked cluster have continued through July 20, 2026.",
"credibility": 82,
"direction": "DOWN",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "CDC reported 4,173 confirmed domestically acquired cases nationally with 308 hospitalizations (~7%) as of July 21, using confirmed-only case definitions.",
"credibility": 85,
"direction": "NEUTRAL",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "web_search",
"strength": "MODERATE",
"sub_question_id": "sq3"
},
{
"claim": "MDHHS updates hospitalization counts only weekly on Thursdays, meaning roughly five more updates fall before August 31, 2026.",
"credibility": 90,
"direction": "NEUTRAL",
"priced_in": true,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "STRONG",
"sub_question_id": "sq2"
},
{
"claim": "Cyclosporiasis is described as not usually life-threatening and treatable with antibiotics; no deaths reported in the 2026 outbreak.",
"credibility": 88,
"direction": "UP",
"priced_in": true,
"recency": "RECENT",
"source": "article_search",
"strength": "MODERATE",
"sub_question_id": "sq3"
},
{
"claim": "MDHHS identified lettuce/salad greens as the likely source on July 13-14 but had not named a specific grower or supplier at that time.",
"credibility": 88,
"direction": "NEUTRAL",
"priced_in": true,
"recency": "RECENT",
"source": "article_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "Michigan\u0027s outbreak spread to 71 of 83 counties by July 24 and is called the worst documented US parasitic foodborne event; state normally sees ~50 cases/year.",
"credibility": 85,
"direction": "DOWN",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "Neighboring states show much lower burdens (Illinois 408 cases/31 hospitalizations; Ohio 361 cases/46 hospitalizations), indicating Michigan\u0027s outbreak is the dominant cluster.",
"credibility": 80,
"direction": "NEUTRAL",
"priced_in": false,
"recency": "VERY_RECENT",
"source": "article_search",
"strength": "WEAK",
"sub_question_id": "sq2"
}
],
"information_gaps": [
"No epidemic-curve data by symptom-onset date (only report date), so true peak timing unknown",
"No base rates for how quickly past large cyclospora/produce outbreaks decayed after recall",
"No data on reporting lag between hospitalization and MDHHS inclusion, or retrospective backfill practice",
"No MDHHS update after July 24; no Kalshi/market pricing provided"
],
"key_uncertainties": [
"Whether the July 20 Taylor Farms recall halted new exposures promptly",
"Whether weekly hospitalization increments stay near +58 or decay quickly",
"Whether MDHHS revises/backfills hospitalization counts upward",
"Plateau case total (12,000+ at ~2% would breach 300)"
],
"n_evidence": 12
},
"timings": {
"forecast": 44.68,
"plan": 26.25,
"research": 32.2,
"synthesis": 32.01
}
}