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: 1%
* Between 500 and 1000: 60%
* Between 1000 and 1500: 20%
* Between 1500 and 2000: 15%
* Greater than 2000: 4%
Obtaining outside data.
Checking internet sources, using keywords: Ukraine conflict deaths June 2025
News from various sources:
The content provided includes information about the conflict in Ukraine as recorded by ACLED (Armed Conflict Location and Event Data) and various sources, notably focusing on civilian and military casualties as of June 2025.
Key Points:
1. **Rising Conflicts Worldwide**: The ACLED report highlights a significant surge in global conflicts in 2024, with over 233,000 estimated deaths worldwide, including the Ukraine conflict.
2. **Casualties in Ukraine**: According to ACLED data, more than 10,000 deaths have been recorded in Ukraine since the conflict began. This includes approximately 3,600 civilian deaths as identified by BBC News as of mid-June, with the UN confirming about 4,700 civilian deaths up to the end of the month.
3. **Challenges in Data Collection**: Both ACLED and the UN acknowledge that these figures likely underestimate the true casualties due to difficulties in data verification amidst ongoing hostilities. The UN also notes additional deaths due to collateral impacts like lack of healthcare.
4. **Locations of Violence**: Southern and eastern regions of Ukraine, particularly Mariupol, Kharkiv, and Bilohorivka, have experienced heavy casualties. Much of the violence is attributed to shelling and air strikes.
5. **Military Deaths**: Information on military casualties is contentious and difficult to verify. Ukraine reportedly loses 100-200 soldiers daily in the Donbas region as per Ukrainian sources, while Russian military death claims and figures fluctuate without independent verification.
6. **War Crimes Allegations**: There are accusations of war crimes, particularly against Russia for targeting civilians, though they deny these claims.
7. **Civilians and Combatants**: The conflict continues to have a severe human cost, impacting both civilians and soldiers significantly. The daily toll underscores the humanitarian crisis.
This information provides a snapshot of the state of the conflict as of mid-2025, demonstrating the complexities and human impact of the ongoing war in Ukraine.
Fact-checking news summary:
1. **Rising Conflicts Worldwide: The ACLED report highlights a significant surge in global conflicts in 2024, with over 233,000 estimated deaths worldwide, including the Ukraine conflict.**
– **Correctness:** Unable to verify (specific to ACLED’s internal data)
– **Importance to Resolution:** Lesser (does not directly contribute to the exact number of deaths in June 2025)
– **Relevance to Outcome:** False (does not directly relate to the specific forecasted figure for June 2025)
2. **Casualties in Ukraine: According to ACLED data, more than 10,000 deaths have been recorded in Ukraine since the conflict began.**
– **Correctness:** True (this figure can be cross-referenced with reports, assuming consistency with data provided)
– **Importance to Resolution:** Important (provides a context of the scale but not specific to June 2025)
– **Relevance to Outcome:** True (relevant to understanding total recorded deaths)
3. **Approximately 3,600 civilian deaths as identified by BBC News as of mid-June 2025, with the UN confirming about 4,700 civilian deaths up to the end of the month.**
– **Correctness:** Unable to verify (specific figures cannot be independently verified)
– **Importance to Resolution:** Important (provides specific recent data points for civilian deaths)
– **Relevance to Outcome:** True (relates to the forecasted figure for June 2025)
4. **Challenges in Data Collection: Both ACLED and the UN acknowledge these figures likely underestimate true casualties due to difficulties in data verification amidst ongoing hostilities. The UN also notes additional deaths due to collateral impacts like lack of healthcare.**
– **Correctness:** True (known issues in conflict casualty estimation)
– **Importance to Resolution:** Important (impacts understanding of potential underreporting)
– **Relevance to Outcome:** True (indicates potential variance in reported numbers)
5. **Locations of Violence: Southern and eastern regions of Ukraine, particularly Mariupol, Kharkiv, and Bilohorivka, have experienced heavy casualties due to shelling and airstrikes.**
– **Correctness:** True (these areas have been consistent sites of conflict)
– **Importance to Resolution:** Lesser (provides geographical context)
– **Relevance to Outcome:** True (relevant in understanding the conflict dynamics)
6. **Military Deaths: Ukraine reportedly loses 100-200 soldiers daily in the Donbas region, while Russian military death figures fluctuate.**
– **Correctness:** Partially true (specific figures are contentious and vary by source)
– **Importance to Resolution:** Lesser (does not directly translate to a total or specific month)
– **Relevance to Outcome:** True (relevant as military deaths affect overall counts)
7. **War Crimes Allegations: Accusations against Russia for targeting civilians, which they deny.**
– **Correctness:** True (documented allegations and denials)
– **Importance to Resolution:** Unimportant (contextual background)
– **Relevance to Outcome:** False (does not contribute to the numerical analysis for June 2025)
8. **Civilians and Combatants: The conflict severely impacts civilians and soldiers, with a daily toll emphasizing the humanitarian crisis.**
– **Correctness:** True (consistent with ongoing reports of humanitarian impact)
– **Importance to Resolution:** Important (underscores total deaths context, though not specific to June 2025)
– **Relevance to Outcome:** True (relevant to the understanding of overall conflict death figures)
Fact-checked summary:
In Ukraine, ACLED data records over 10,000 deaths since the conflict’s onset, highlighting the scale of casualty impact, although not specific to June 2025. The UN confirms approximately 4,700 civilian deaths by the end of June 2025, contextualizing recent casualties. Challenges in data collection acknowledged by ACLED and the UN suggest these figures might underestimate the true toll, emphasizing potential discrepancies in reported numbers. Significant violence has been concentrated in southern and eastern regions, including Mariupol, Kharkiv, and Bilohorivka, which consistently experience high casualties. The ongoing conflict heavily impacts both civilians and combatants, amplifying the humanitarian crisis, and these elements are important for understanding total conflict death figures.
OpenAI gives a base rate of Probability of reaching between 500 and 1000 deaths in June 2025
The question difficulty is rated 6 (0 to 10)
Historical weighted factors include:
Average monthly deaths in Ukraine conflict over the previous few months, 0.4
Reported civilian and combatant deaths, 0.3
Intensity of ongoing military conflicts, 0.3
A Bayesian calculation could be performed as follows:
Using historical factors, the prior probability of the ‘Between 500 and 1000 deaths’ scenario is high given typical monthly death counts around 1000. Considering news suggesting 4700 deaths by June 25, assume approximately 500 deaths monthly. This prior informed by specific regional violence.
Bayesian base rate: 0.85
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: reference_class
Expected time (days) until question close: 13
The following were considered in order to produce this base rate:
The base rate was derived from reviewing historical death counts in the Ukraine conflict, which consistently approached or exceeded the 500-mark monthly. ACLED and UN data provide insight into shifting casualty figures, strongly supporting a death count between 500 and 1000 for June 2025.
Ideally, the news feed would contain the following sorts of information for a better forecast:
More precise data on daily casualty rates would refine the forecast. Information on ceasefire agreements or unexpected diplomatic outcomes could significantly adjust expected casualty numbers.
Some potential divergent considerations that might affect the base rate:
If data collection discrepancies are larger than anticipated, the actual death count could vary outside the anticipated range, potentially pushing above 1000.
The following chain of events are necessary for the question to resolve positively:
– More than 500 deaths occurring in June 2025 (almost certain).
– Less than 1000 deaths occurring in June 2025 (likely based on current reports).
Querying Claude (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.45, “Between 1000 and 1500”: 0.3, “Between 1500 and 2000”: 0.15, “Greater than 2000”: 0.05] – confidence: 6)
Querying Mistral (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.85, “Between 1000 and 1500”: 0.1, “Between 1500 and 2000”: 0.03, “Greater than 2000”: 0.01] – confidence: 7)
Querying OpenAI (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.6, “Between 1000 and 1500”: 0.2, “Between 1500 and 2000”: 0.15, “Greater than 2000”: 0.04] – confidence: 7)
Question Type: Multiple Choice
Confidence: 7
MAPD: Avg: 0.10666666666667, Max: 0.26666666666667
# LLM responses: 3
Explanations of the above statistical measures here —>
Model value:
* Less than 500: 1%
* Between 500 and 1000: 60%
* Between 1000 and 1500: 20%
* Between 1500 and 2000: 15%
* Greater than 2000: 4%
The predictions for conflict deaths in Ukraine for June 2025 are primarily derived from historical data and established reporting patterns by ACLED and UN, which typically range between 500 and 1000 deaths monthly. This estimate considers ongoing combat in high-casualty regions like Mariupol and Kharkiv, while acknowledging potential inaccuracies due to challenges in data collection. There is a consistent expectation based on past trends of death counts approaching or surpassing 500, supported by reports indicating such likelihood. Uncertainty in the prediction arises from possible unforeseen changes in the conflict’s intensity, data collection methodologies, and potential biases or errors in data reporting. Additionally, changes in conflict dynamics or peace negotiations could significantly alter the predicted casualty figures outside the anticipated range.
Runtime: 118 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/
