How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in June, 2025?
Here’s what Jeremy’s Multi-AI Oracle predicts today:
* Less than 500: 5%
* Between 500 and 1000: 21%
* Between 1000 and 1500: 37%
* Between 1500 and 2000: 26%
* Greater than 2000: 11%
Obtaining outside data.
Checking internet sources, using keywords: Ukraine conflict deaths June 2025
Results from various sources:
{think}
The relevant information regarding the Ukraine conflict and related deaths from the provided content is as follows:
– Russian Foreign Minister Sergei Lavrov and U.S. Secretary of State Marco Rubio held a phone call to discuss efforts to resolve the ongoing Russia-Ukraine conflict. This conversation was part of preparations for renewed negotiations between Russia and Ukraine, scheduled for June 2, 2025, in Istanbul, Turkey.
– The discussion emphasized diplomatic initiatives aimed at ending the war, in its third year, and covered the recent deadly attacks within Russian territory. Rubio expressed condolences for the deaths and injuries caused by the destruction of two bridges near the Ukraine border, which resulted in seven deaths and 69 injuries.
– Both sides are under international pressure to reduce tensions and seek a diplomatic path forward. The upcoming talks in Istanbul are seen as an important opportunity to revive peace efforts amidst increasing hostilities.
This summary focuses on the key points related to the Ukraine conflict and deaths, while excluding irrelevant links, news headlines, and other unrelated information from the original content.
Fact-checking news summary:
Based on the provided summary, the following are specific facts along with their evaluations:
1. **Fact**: Russian Foreign Minister Sergei Lavrov and U.S. Secretary of State Marco Rubio held a phone call to discuss the Russia-Ukraine conflict.
– **Correctness**: False. Marco Rubio is a U.S. Senator, not the Secretary of State. The U.S. Secretary of State, as of the last update, was Antony Blinken.
– **Importance**: Lesser to the resolution of the question.
– **Relevance**: False. This fact does not directly relate to the number of conflict deaths reported by ACLED in June 2025.
2. **Fact**: Negotiations between Russia and Ukraine are scheduled for June 2, 2025, in Istanbul, Turkey.
– **Correctness**: Unknown. This is a future event and cannot be verified without additional external information.
– **Importance**: Lesser to the resolution of the question.
– **Relevance**: True. Diplomatic efforts could influence conflict dynamics and subsequently affect conflict deaths.
3. **Fact**: The ongoing Russia-Ukraine war is in its third year.
– **Correctness**: True, given that the conflict began in February 2022.
– **Importance**: Lesser to the resolution of the question.
– **Relevance**: True. The duration of the conflict may affect its intensity and death toll.
4. **Fact**: Recent deadly attacks within Russian territory resulted in the destruction of two bridges near the Ukraine border, causing seven deaths and 69 injuries.
– **Correctness**: Unknown. Without additional context or sources, the specifics of these events cannot be verified.
– **Importance**: Important to the resolution of the question, as it pertains to conflict-related deaths.
– **Relevance**: False. Deaths within Russian territory may not be included in the ACLED count for Ukraine.
5. **Fact**: The upcoming talks in Istanbul are seen as an opportunity to revive peace efforts amidst increasing hostilities.
– **Correctness**: True, as diplomatic talks generally aim to reduce conflicts.
– **Importance**: Important to the resolution of the question.
– **Relevance**: True. Successful peace talks could potentially reduce state-based conflict deaths in Ukraine.
While these facts provide context to the situation in Ukraine, the key question regarding the total number of state-based conflict deaths reported by ACLED hinges on future conflict dynamics and reporting practices, which are not directly addressed in the summary.
Fact-checked summary:
In June 2025, the ongoing Russia-Ukraine war will be in its third year, as the conflict began in February 2022. This duration may affect the conflict’s intensity and, consequently, the death toll. Additionally, upcoming talks in Istanbul are viewed as an opportunity to revive peace efforts amidst increasing hostilities. Successful diplomatic talks could potentially reduce state-based conflict deaths in Ukraine, which is relevant to understanding potential changes in conflict dynamics that may affect the ACLED reports.
OpenAI gives a base rate of likelihood of deaths > 1000 (Carolyn‘s note: OpenAI failed to return a value. See the fallback Bayesian base rate calculation below.)
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Duration of conflict, 0.4
Historical monthly death toll, 0.3
Diplomatic efforts, 0.2
Military aid and resources, 0.1
A Bayesian calculation could be performed as follows:
The calculation starts with a historical base rate, refined by updating with current circumstances. Historical monthly death toll for this conflict shows an average likelihood of over 1000 fatalities per month, especially in active periods. With the added event of ongoing talks potentially influencing this, we weigh the increased probability the talks will fail and use 0.9 (from historical data that favors high casualties) * 0.8 (adjustment for current peace talks likely failing) => approximate Bayesian probability is 72%
Bayesian base rate: 72%
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 27
The following were considered in order to produce this base rate:
The base rate of over 1000 monthly deaths is derived from analyzing similar periods of high-intensity fighting in the Russia-Ukraine conflict. Historical data shows a likelihood of this magnitude of fatalities substantiated by past reports from ACLED.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional intelligence data or insights from involved diplomatic figures on the success likelihood of the upcoming talks would be valuable. Also, any sudden changes in military strategy or unexpected external interventions could shift the forecast significantly.
Some potential divergent considerations that might affect the base rate:
If the talks in Istanbul find unexpected success, reducing hostilities significantly, or if there is a sudden ceasefire, the fatalities could drop below 500, diverging from the current prediction.
The following chain of events are necessary for the question to resolve positively:
– Continuation of the conflict between Russia and Ukraine throughout June 2025, with a similar or increased intensity compared to previous months – Likely
– Breakdown of diplomatic efforts such as the talks in Istanbul, thus failing to reduce hostilities – Possible
Querying Claude (AI predicts: [“Less than 500”: 0.15, “Between 500 and 1000”: 0.25, “Between 1000 and 1500”: 0.35, “Between 1500 and 2000”: 0.2, “Greater than 2000”: 0.05] – confidence: 4)
Querying Mistral (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.2, “Between 1000 and 1500”: 0.4, “Between 1500 and 2000”: 0.25, “Greater than 2000”: 0.1] – confidence: 6)
Querying OpenAI (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.15, “Between 1000 and 1500”: 0.3, “Between 1500 and 2000”: 0.25, “Greater than 2000”: 0.25] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.073333333333333, Max: 0.13333333333333
# LLM responses: 3
Explanations of the above statistical measures here —>
Model value:
* Less than 500: 5%
* Between 500 and 1000: 21%
* Between 1000 and 1500: 37%
* Between 1500 and 2000: 26%
* Greater than 2000: 11%
The predictions across the different AIs primarily hinge on the ongoing conflict intensity between Russia and Ukraine, drawing from historical ACLED data which suggests a likelihood of more than 1000 monthly deaths during sustained high-intensity situations. Factors such as war fatigue, stabilization of front lines, and peace talks in Istanbul are highlighted as potential elements influencing casualty rates, with the talks offering a chance to reduce hostilities. However, there is a consensus that without significant diplomatic breakthroughs or unforeseen events, the high death toll will likely continue. Errors in these predictions could arise from unexpected success in Istanbul negotiations, leading to reduced casualties, or from an escalation in fighting if diplomatic efforts fail or international dynamics shift. The reliability of ACLED data and potential deviations from historical norms due to external interventions or changes in reporting methodology also complicate the prediction landscape.
Runtime: 114 seconds
Past forecasts by Phil’s and Jeremy ’s bots —>
Jeremy’s Ukraine forecasts are a side experiment with the VIEWS competition. The VIEWS Ukraine dashboard is pictured below. (Carolyn’s note: VIEWS is using ACLED data to score its competitors, given the tendency of nations to minimize their own fatalities and exaggerating those of their enemies.)
Source: Views machine forecasting competition https://data.viewsforecasting.org/
