Show full JSON
{
"forecast": {
"combination_logic": "weighted_average",
"evidence_brief": "1. [sq1 | description | STRONG cred 90 | NEUTRAL | DATED] July 2023 holds the record at 16.95\u00b0C, with July 2024 close behind at 16.91\u00b0C and July 2025 at 16.68\u00b0C.\n2. [sq1 | description | MODERATE cred 85 | DOWN | RECENT] 2026 monthly anomalies (Feb +0.53, Mar +0.53, Apr +0.52) are moderate, ranking 3rd-5th warmest rather than record-setting.\n3. [sq2 | description | MODERATE cred 70 | UP | RECENT] ENSO is forecast to transition to a \u0027very strong\u0027 El Ni\u00f1o in the second half of 2026, putting upward pressure on global temperatures.\n4. [sq1 | description | MODERATE cred 80 | UP | DATED] July 2023\u0027s record was set during an El Ni\u00f1o, providing precedent that strong El Ni\u00f1o Julys can break records.\n5. [sq1 | description | MODERATE cred 85 | DOWN | DATED] Beating the record requires exceeding July 2023\u0027s 16.95\u00b0C; July 2025 was 0.27\u00b0C below that mark.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.72, Volume: $2.8M\n- \"Strait of Hormuz traffic returns to normal by July 31?\" \u2192 Yes: 0.46, Volume: $6.8M\n- \"Strait of Hormuz traffic returns to normal by July 15?\" \u2192 Yes: 0.24, Volume: $1.4M\n- \" Iran agrees to end enrichment of uranium by July 31?\" \u2192 Yes: 0.14, Volume: $521.8K\n\nInformation gaps:\n - No actual May/June 2026 anomaly data to gauge mid-year trajectory\n - No confirmed El Ni\u00f1o onset timing or strength update for summer 2026\n - No model forecasts specifically projecting July 2026 global temperature\n - Base rate: how often do moderate-anomaly years break July records\n\nKey uncertainties:\n - Whether El Ni\u00f1o strengthens fast enough to impact July\n - Magnitude of warming needed to overtake 2023 record\n - Whether 2026 anomaly trend accelerates in summer",
"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 July 2026 be the warmest July on record, according to Copernicus?\n\n## Description / Resolution Criteria\n## Description\nAccording to the Copernicus Climate Change Service (C3S):\n\n\u003e The C3S mission is to support adaptation and mitigation policies of the European Union by providing consistent and authoritative information about climate change. We offer free and open access to climate data and tools based on the best available science. We listen to our users and endeavour to help them meet their goals in dealing with the impacts of climate change.\n\nJuly 2023 set a record for the warmest July at the time, with a global average surface air temperature of 16.95\u00b0C, which was 0.72\u00b0C above the 1991\u20132020 average and approximately 1.48\u00b0C above the 1850\u20131900 pre-industrial baseline.\n\nJuly 2024 was the second-warmest July on record at 16.91\u00b0C, which was 0.68\u00b0C above 1991\u20132020 (only 0.04\u00b0C cooler than July 2023).\n\nJuly 2025 was 16.68\u00b0C, the third warmest July at the time.\u0026#x20;\n\nIn 2026, monthly anomalies vs. 1991\u20132020 have been moderate compared to 2023\u201324:\n\n\\- February 2026: +0.53\u00b0C (5th warmest February)\n\n\\- March 2026: +0.53\u00b0C (4th warmest March)\n\n\\- April 2026: +0.52\u00b0C (3rd-warmest April)\n\nIn the second half of 2026, the El Ni\u00f1o Southern Oscillation (ENSO) is [forecast](https://www.noaa.gov/news-release/el-nino-forms-expected-to-strengthen-say-noaa-forecasters) to transition to a \"very strong\" El Ni\u00f1o, which could put significant upward pressure on global temperatures.\n\n`{\"format\": \"metac_reveal_and_close_in_period\", \"info\": {\"post_id\": 43992, \"question_id\": 44017}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** July 2026 is the warmest July on record in the ERA5 [dataset](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels?tab=overview), according to the Copernicus Climate Change Service (C3S) monthly [Climate Bulletin](https://climate.copernicus.eu/climate-bulletin) covering July 2026.\u0026#x20;\n\n## Fine Print\nA tie will resolve as **Yes**.\u0026#x20;\n\n***\nThis question\u0027s information (resolution criteria, fine print, background info, etc) is synced with an [original identical question](https://www.metaculus.com/questions/43992) which opened on 2026-06-13 03:00:00. 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(none)\n\nCombination rule: **weighted_average**\n\n## Synthesized evidence\n1. [sq1 | description | STRONG cred 90 | NEUTRAL | DATED] July 2023 holds the record at 16.95\u00b0C, with July 2024 close behind at 16.91\u00b0C and July 2025 at 16.68\u00b0C.\n2. [sq1 | description | MODERATE cred 85 | DOWN | RECENT] 2026 monthly anomalies (Feb +0.53, Mar +0.53, Apr +0.52) are moderate, ranking 3rd-5th warmest rather than record-setting.\n3. [sq2 | description | MODERATE cred 70 | UP | RECENT] ENSO is forecast to transition to a \u0027very strong\u0027 El Ni\u00f1o in the second half of 2026, putting upward pressure on global temperatures.\n4. [sq1 | description | MODERATE cred 80 | UP | DATED] July 2023\u0027s record was set during an El Ni\u00f1o, providing precedent that strong El Ni\u00f1o Julys can break records.\n5. [sq1 | description | MODERATE cred 85 | DOWN | DATED] Beating the record requires exceeding July 2023\u0027s 16.95\u00b0C; July 2025 was 0.27\u00b0C below that mark.\n\n## Cross-Market Signals\n\n### Polymarket\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.72, Volume: $2.8M\n- \"Strait of Hormuz traffic returns to normal by July 31?\" \u2192 Yes: 0.46, Volume: $6.8M\n- \"Strait of Hormuz traffic returns to normal by July 15?\" \u2192 Yes: 0.24, Volume: $1.4M\n- \" Iran agrees to end enrichment of uranium by July 31?\" \u2192 Yes: 0.14, Volume: $521.8K\n\nInformation gaps:\n - No actual May/June 2026 anomaly data to gauge mid-year trajectory\n - No confirmed El Ni\u00f1o onset timing or strength update for summer 2026\n - No model forecasts specifically projecting July 2026 global temperature\n - Base rate: how often do moderate-anomaly years break July records\n\nKey uncertainties:\n - Whether El Ni\u00f1o strengthens fast enough to impact July\n - Magnitude of warming needed to overtake 2023 record\n - Whether 2026 anomaly trend accelerates in summer\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\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": 0.16,
"models": [
"opus"
],
"p_yes": 0.16,
"rationale": "(a) The question resolves after July 2026 data is published in early August 2026; the early-2026 monthly data (through April) is already known. (b) Status quo: 2026 monthly anomalies are running at roughly +0.52 to +0.53\u00b0C vs 1991\u20132020, well below the +0.72\u00b0C anomaly that set the July 2023 record and below July 2024 (+0.68). At this trajectory, July 2026 tracks closer to July 2025 (16.68\u00b0C), which fell 0.27\u00b0C short of the record. (c) NO scenario: El Ni\u00f1o develops slowly or its global temperature impact lags into late 2026, so July remains in the moderate band consistent with current anomalies, landing 2nd\u20134th warmest but short of 16.95\u00b0C. (d) YES scenario: A rapidly strengthening \u0027very strong\u0027 El Ni\u00f1o combines with the underlying warming trend to produce an anomalous spike in July, pushing the anomaly up ~0.2\u00b0C to exceed 2023. (e) The gap to close is large (~0.2\u00b0C), early-2026 data is the strongest signal and points DOWN, while the El Ni\u00f1o forecast is uncertain and may not fully manifest by July. Net: below even odds, weighted toward NO.",
"sub_question_estimates": {
"sq1": 0.16
},
"what_would_change_my_mind": "Confirmed May/June 2026 anomalies climbing toward +0.65\u20130.70\u00b0C, or a confirmed rapid \u0027very strong\u0027 El Ni\u00f1o onset by early summer, would push me above 30%; continued moderate anomalies (~+0.5\u00b0C) would keep me below 15%."
},
"plan": {
"combination_logic": "weighted_average",
"domain": "unknown",
"n_sub_qs": 0,
"n_tools": 0,
"reasoning_approach": "",
"sub_questions": [],
"tool_requests": []
},
"question": {
"close_time": "2026-06-20T03:00:00Z",
"description": "## Description\nAccording to the Copernicus Climate Change Service (C3S):\n\n\u003e The C3S mission is to support adaptation and mitigation policies of the European Union by providing consistent and authoritative information about climate change. We offer free and open access to climate data and tools based on the best available science. We listen to our users and endeavour to help them meet their goals in dealing with the impacts of climate change.\n\nJuly 2023 set a record for the warmest July at the time, with a global average surface air temperature of 16.95\u00b0C, which was 0.72\u00b0C above the 1991\u20132020 average and approximately 1.48\u00b0C above the 1850\u20131900 pre-industrial baseline.\n\nJuly 2024 was the second-warmest July on record at 16.91\u00b0C, which was 0.68\u00b0C above 1991\u20132020 (only 0.04\u00b0C cooler than July 2023).\n\nJuly 2025 was 16.68\u00b0C, the third warmest July at the time.\u0026#x20;\n\nIn 2026, monthly anomalies vs. 1991\u20132020 have been moderate compared to 2023\u201324:\n\n\\- February 2026: +0.53\u00b0C (5th warmest February)\n\n\\- March 2026: +0.53\u00b0C (4th warmest March)\n\n\\- April 2026: +0.52\u00b0C (3rd-warmest April)\n\nIn the second half of 2026, the El Ni\u00f1o Southern Oscillation (ENSO) is [forecast](https://www.noaa.gov/news-release/el-nino-forms-expected-to-strengthen-say-noaa-forecasters) to transition to a \"very strong\" El Ni\u00f1o, which could put significant upward pressure on global temperatures.\n\n`{\"format\": \"metac_reveal_and_close_in_period\", \"info\": {\"post_id\": 43992, \"question_id\": 44017}}`\n\n## Resolution Criteria\nThis question resolves as **Yes** July 2026 is the warmest July on record in the ERA5 [dataset](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels?tab=overview), according to the Copernicus Climate Change Service (C3S) monthly [Climate Bulletin](https://climate.copernicus.eu/climate-bulletin) covering July 2026.\u0026#x20;\n\n## Fine Print\nA tie will resolve as **Yes**.\u0026#x20;\n\n***\nThis question\u0027s information (resolution criteria, fine print, background info, etc) is synced with an [original identical question](https://www.metaculus.com/questions/43992) which opened on 2026-06-13 03:00:00. 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 July 2026 be the warmest July on record, according to Copernicus?"
},
"research": {
"cross_market_brief": "## Cross-Market Signals\n\n### Polymarket\n- \"Will there be no change in Fed interest rates after the July 2026 meeting?\" \u2192 Yes: 0.72, Volume: $2.8M\n- \"Strait of Hormuz traffic returns to normal by July 31?\" \u2192 Yes: 0.46, Volume: $6.8M\n- \"Strait of Hormuz traffic returns to normal by July 15?\" \u2192 Yes: 0.24, Volume: $1.4M\n- \" Iran agrees to end enrichment of uranium by July 31?\" \u2192 Yes: 0.14, Volume: $521.8K",
"errors": [],
"has_cross_market": true,
"n_errors": 0,
"n_tools": 0,
"tools": []
},
"synthesis": {
"evidence": [
{
"claim": "July 2023 holds the record at 16.95\u00b0C, with July 2024 close behind at 16.91\u00b0C and July 2025 at 16.68\u00b0C.",
"credibility": 90,
"direction": "NEUTRAL",
"priced_in": true,
"recency": "DATED",
"source": "description",
"strength": "STRONG",
"sub_question_id": "sq1"
},
{
"claim": "2026 monthly anomalies (Feb +0.53, Mar +0.53, Apr +0.52) are moderate, ranking 3rd-5th warmest rather than record-setting.",
"credibility": 85,
"direction": "DOWN",
"priced_in": true,
"recency": "RECENT",
"source": "description",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "ENSO is forecast to transition to a \u0027very strong\u0027 El Ni\u00f1o in the second half of 2026, putting upward pressure on global temperatures.",
"credibility": 70,
"direction": "UP",
"priced_in": true,
"recency": "RECENT",
"source": "description",
"strength": "MODERATE",
"sub_question_id": "sq2"
},
{
"claim": "July 2023\u0027s record was set during an El Ni\u00f1o, providing precedent that strong El Ni\u00f1o Julys can break records.",
"credibility": 80,
"direction": "UP",
"priced_in": true,
"recency": "DATED",
"source": "description",
"strength": "MODERATE",
"sub_question_id": "sq1"
},
{
"claim": "Beating the record requires exceeding July 2023\u0027s 16.95\u00b0C; July 2025 was 0.27\u00b0C below that mark.",
"credibility": 85,
"direction": "DOWN",
"priced_in": true,
"recency": "DATED",
"source": "description",
"strength": "MODERATE",
"sub_question_id": "sq1"
}
],
"information_gaps": [
"No actual May/June 2026 anomaly data to gauge mid-year trajectory",
"No confirmed El Ni\u00f1o onset timing or strength update for summer 2026",
"No model forecasts specifically projecting July 2026 global temperature",
"Base rate: how often do moderate-anomaly years break July records"
],
"key_uncertainties": [
"Whether El Ni\u00f1o strengthens fast enough to impact July",
"Magnitude of warming needed to overtake 2023 record",
"Whether 2026 anomaly trend accelerates in summer"
],
"n_evidence": 5
},
"timings": {
"forecast": 19.78,
"plan": 26.01,
"research": 0.79,
"synthesis": 10.16
}
}