OSINT

Early claims, source checks, and account track records
OSINT feed Fast OSINT is only for current or near-current claims. AI checks run immediately, then at 1h, 6h, and 24h; older research-style items should be posted normally.
verified OSINT claim 65% verification - developing Track 39 establishing Signal 75
Verification details 65% developing
Verification 65%: Multiple sources confirm IDF announced strikes targeting two senior Hamas operatives in northern Gaza on May 27, 2026, closely matching the claim's timing and content. All sources rely on IDF statements without independent verification of operative identities or strike outcomes.

Multiple sources confirm IDF announced strikes targeting two senior Hamas operatives in northern Gaza on May 27, 2026, closely matching the claim's timing and content. All sources rely on IDF statements without independent verification of operative identities or strike outcomes.

Evidence 42 AI 67 Track prior 47 4 resolved OSINT posts 25.0% false-positive/noise rate Source reliability 42 Bias balance 57 0 trusted sources
  • Trusted-source evidence score: 42.0
  • OSINT track record prior: 47.0
  • Checked window: 2026-05-27 13:49 through 2026-05-28 14:49.
  • AI evidence review score: 67.5
The IDF says it struck two key Hamas operatives in northern Gaza.
OSINT quality 78 73-82
Scored for discipline, source tier, information density, confidence signaling, coherence, and redundancy.
Claude 73 ChatGPT 82
  • This is a straightforward relay of an IDF statement about a military strike. The attribution is clear ("IDF says"), which provides minimal epistemic transparency, but as OSINT content it lacks source links, timestamp, or verification pathway. The claim itself is Tier 2: the IDF making this statement is likely documentable, but the underlying factual claim (that the strike occurred and hit the stated targets) remains
  • The statement is narrowly framed as an attributed claim (“IDF says”), which is epistemically safer than asserting the strike as confirmed fact. However, it lacks basic grounding details (when/where, which IDF release, names/roles of operatives), limiting verifiability and OSINT usefulness.
Claude raw JSON 73
{
    "overall": 72,
    "content_type": "reported-fact",
    "rhetorical_intent": "inform",
    "dimensions": {
        "claim_honesty": 75,
        "logical_integrity": 85,
        "epistemic_transparency": 60,
        "communicative_effectiveness": 70,
        "grounding_adequacy": 65
    },
    "flags": [
        {
            "type": "warning",
            "text": "Attribution to IDF present but no independent verification or source link provided for OSINT content"
        },
        {
            "type": "info",
            "text": "Claim tier: Tier 2 (documented but contestable) - IDF statements are public record but represent one party's account in active conflict"
        },
        {
            "type": "caution",
            "text": "No epistemic hedging beyond attribution - reader cannot assess claim strength or verify independently"
        }
    ],
    "reasoning": "This is a straightforward relay of an IDF statement about a military strike. The attribution is clear (\"IDF says\"), which provides minimal epistemic transparency, but as OSINT content it lacks source links, timestamp, or verification pathway. The claim itself is Tier 2: the IDF making this statement is likely documentable, but the underlying factual claim (that the strike occurred and hit the stated targets) remains unverified and represents one combatant's account. For reported-fact content, especially OSINT, grounding adequacy suffers without source access."
}
ChatGPT raw JSON 82
{
    "overall": 78,
    "content_type": "reported-fact",
    "rhetorical_intent": "inform",
    "dimensions": {
        "claim_honesty": 85,
        "logical_integrity": 90,
        "epistemic_transparency": 80,
        "communicative_effectiveness": 70,
        "grounding_adequacy": 60
    },
    "flags": [
        {
            "type": "sourcing_absent",
            "text": "No link, date, or statement excerpt is provided to verify what the IDF said."
        },
        {
            "type": "attribution_limited",
            "text": "The claim is attributed to the IDF, but it does not clarify whether this is confirmed independently or only an official assertion."
        }
    ],
    "reasoning": "The statement is narrowly framed as an attributed claim (“IDF says”), which is epistemically safer than asserting the strike as confirmed fact. However, it lacks basic grounding details (when/where, which IDF release, names/roles of operatives), limiting verifiability and OSINT usefulness."
}
What we measure
0
$
Scoring calls: $0.013709
AI Score In Out Total ms $
Claude 73 1166 372 1538 11915 0.009078
ChatGPT 82 1070 197 1267 3601 0.004631
~ estimated where historical API usage was unavailable
Verification calls: $0.023161
AI Provider In Out Total $
claude-sonnet-4-5 anthropic 1170 688 1858 0.013830
gpt-5.2 openai 1188 518 1706 0.009331
verified OSINT claim 64% verification - developing Track 39 establishing Signal 75
Verification details 64% developing
Verification 64%: IDF confirmed striking two senior Hamas operatives in northern Gaza on May 27, 2026, matching the claim's timeframe. Times of Israel and i24NEWS corroborate the core event within hours of the post. Specific identities as Northern Gaza Brigade commander and Gaza City deputy commander lack independent confirmation in provided sources.

IDF confirmed striking two senior Hamas operatives in northern Gaza on May 27, 2026, matching the claim's timeframe. Times of Israel and i24NEWS corroborate the core event within hours of the post. Specific identities as Northern Gaza Brigade commander and Gaza City deputy commander lack independent confirmation in provided sources.

Evidence 40 AI 65 Track prior 38 4 resolved OSINT posts 25.0% false-positive/noise rate Source reliability 42 Bias balance 50 0 trusted sources
  • Trusted-source evidence score: 40.0
  • OSINT track record prior: 38.0
  • Checked window: 2026-05-27 13:51 through 2026-05-28 14:51.
  • AI evidence review score: 64.7
IDF struck two senior Hamas figures in northern Gaza. Gaza sources identify them as the Northern Gaza Brigade commander and Gaza City deputy commander.
OSINT quality 71 70-72
Scored for discipline, source tier, information density, confidence signaling, coherence, and redundancy.
ChatGPT 70 Claude 72
  • The post makes concrete, news-like claims about a strike and the identities/roles of those targeted, but provides no sourcing and uses vague attribution (“Gaza sources”). It is internally coherent and clearly intended to inform, yet it lacks transparency about confidence and verification for a contested, high-stakes identification.
  • This OSINT post reports a military strike and identifies specific Hamas commanders but provides no verifiable sourcing beyond 'Gaza sources.' While the factual tone suggests Tier 2 claims, the lack of attribution transparency undermines epistemic honesty. For OSINT content, source identification is critical to grounding adequacy. The post is clear and concise but fails to signal uncertainty or provide readers means t
ChatGPT raw JSON 70
{
    "overall": 62,
    "content_type": "reported-fact",
    "rhetorical_intent": "inform",
    "dimensions": {
        "claim_honesty": 70,
        "logical_integrity": 85,
        "epistemic_transparency": 55,
        "communicative_effectiveness": 75,
        "grounding_adequacy": 30
    },
    "flags": [
        {
            "type": "unsourced_claim",
            "text": "No sources or links provided for the IDF strike or the identification of the individuals."
        },
        {
            "type": "attribution_vagueness",
            "text": "\"Gaza sources\" is vague and does not specify which outlets/officials or how the identification was made."
        },
        {
            "type": "verification_gap",
            "text": "Identities/roles of \"two senior Hamas figures\" are contestable and require stronger corroboration than provided."
        }
    ],
    "reasoning": "The post makes concrete, news-like claims about a strike and the identities/roles of those targeted, but provides no sourcing and uses vague attribution (“Gaza sources”). It is internally coherent and clearly intended to inform, yet it lacks transparency about confidence and verification for a contested, high-stakes identification."
}
Claude raw JSON 72
{
    "overall": 72,
    "content_type": "reported-fact",
    "rhetorical_intent": "inform",
    "dimensions": {
        "claim_honesty": 70,
        "logical_integrity": 85,
        "epistemic_transparency": 60,
        "communicative_effectiveness": 75,
        "grounding_adequacy": 65
    },
    "flags": [
        {
            "type": "warning",
            "text": "Attribution to 'Gaza sources' is vague and unverifiable without specific sourcing details"
        },
        {
            "type": "info",
            "text": "IDF strike claim presented as fact without independent confirmation or sourcing"
        },
        {
            "type": "caution",
            "text": "Identities and roles of targeted individuals stated definitively despite relying on unnamed sources"
        }
    ],
    "reasoning": "This OSINT post reports a military strike and identifies specific Hamas commanders but provides no verifiable sourcing beyond 'Gaza sources.' While the factual tone suggests Tier 2 claims, the lack of attribution transparency undermines epistemic honesty. For OSINT content, source identification is critical to grounding adequacy. The post is clear and concise but fails to signal uncertainty or provide readers means to verify the intelligence independently."
}
What we measure
0
$
Scoring calls: $0.013438
AI Score In Out Total ms $
ChatGPT 70 1082 225 1307 4121 0.005044
Claude 72 1178 324 1502 7458 0.008394
~ estimated where historical API usage was unavailable
Verification calls: $0.029203
AI Provider In Out Total $
claude-sonnet-4-5 anthropic 1409 910 2319 0.017877
gpt-5.2 openai 1408 633 2041 0.011326
verified OSINT claim 25% verification - uncertain Track 39 establishing Signal 75
Verification details 25% uncertain
Verification 25%: The claim asserts cutting deals with Iran is unwise but provides no specifics about which deal, when, or by whom. The single source discusses Iran policy broadly without confirming any actual deal negotiation or agreement during the check window. No corroborating evidence supports a specific deal event.

The claim asserts cutting deals with Iran is unwise but provides no specifics about which deal, when, or by whom. The single source discusses Iran policy broadly without confirming any actual deal negotiation or agreement during the check window. No corroborating evidence supports a specific deal event.

Evidence 20 AI 0 Track prior 58 4 resolved OSINT posts 25.0% false-positive/noise rate Source reliability 42 Bias balance 35 0 trusted sources
  • Trusted-source evidence score: 20.0
  • OSINT track record prior: 58.0
  • Checked window: 2026-05-27 13:48 through 2026-05-28 14:48.
  • AI evidence review score: 0.0
Not the best idea to be cutting deals with Iran.
OSINT quality 53 41-65
Scored for discipline, source tier, information density, confidence signaling, coherence, and redundancy.
Claude 41 ChatGPT 65
  • Promotional/branded ad-like content is downranked by policy.
  • The comment asserts as fact that deals are being cut with Iran, but provides no evidence, sourcing, or epistemic hedging. The attached image shows a formal portrait with no visible connection to negotiations or agreements. The normative critique is valid opinion, but it's built on an ungrounded factual claim presented with false certainty. For a standalone post flagged as OSINT, this lacks the discipline and transpar
  • Image appears to be a formal portrait of a Middle Eastern leader/official seated on an ornate throne-like chair, suggesting a real-world political context.
  • The post text references Iran and political deal-making; the image loosely supports a geopolitical theme but does not specifically show Iran or any deal/meeting.
Claude raw JSON 41
{
    "overall": 42,
    "content_type": "polemic",
    "rhetorical_intent": "critique",
    "dimensions": {
        "claim_honesty": 35,
        "logical_integrity": 40,
        "epistemic_transparency": 30,
        "communicative_effectiveness": 65,
        "grounding_adequacy": 50
    },
    "flags": [
        {
            "type": "critical",
            "text": "Core claim ('cutting deals with Iran') presented as settled fact (Tier 1) without evidence that any deal exists or is being negotiated."
        },
        {
            "type": "critical",
            "text": "Zero epistemic transparency: no signal that this is speculation, interpretation, or opinion about a potential future action."
        },
        {
            "type": "warning",
            "text": "Image shows a Middle Eastern official but provides no specific evidence of Iran or any deal-making activity; visual context does not substantiate the claim."
        },
        {
            "type": "info",
            "text": "Normative judgment ('not the best idea') is legitimate opinion, but rests on an unestablished factual premise."
        }
    ],
    "reasoning": "The comment asserts as fact that deals are being cut with Iran, but provides no evidence, sourcing, or epistemic hedging. The attached image shows a formal portrait with no visible connection to negotiations or agreements. The normative critique is valid opinion, but it's built on an ungrounded factual claim presented with false certainty. For a standalone post flagged as OSINT, this lacks the discipline and transparency expected."
}
ChatGPT raw JSON 65
{
    "overall": 62,
    "content_type": "polemic",
    "rhetorical_intent": "critique",
    "dimensions": {
        "claim_honesty": 70,
        "logical_integrity": 55,
        "epistemic_transparency": 75,
        "communicative_effectiveness": 60,
        "grounding_adequacy": 50
    },
    "flags": [
        {
            "type": "vagueness",
            "text": "The comment warns against 'cutting deals with Iran' but gives no specifics about which deal, actors, timeframe, or why it is a bad idea."
        },
        {
            "type": "unsupported_assertion",
            "text": "Implies a negative judgment about deal-making with Iran without providing evidence or reasoning."
        },
        {
            "type": "image_context_gap",
            "text": "Attached image appears to be a formal portrait of a Middle Eastern official, but it does not substantiate any specific claim about Iran or negotiations."
        }
    ],
    "reasoning": "This is a broad, opinionated warning rather than a verifiable factual claim, and it does not misstate concrete facts. However, it offers no argument or context to support the critique, and the image only loosely signals geopolitics without grounding the implied claim about a specific deal."
}
What we measure
0
$
Scoring calls: $0.015721
AI Score In Out Total ms $
Claude 41 1414 396 1810 9598 0.010182
ChatGPT 65 1293 234 1527 3729 0.005539
~ estimated where historical API usage was unavailable
Verification calls: $0.016260
AI Provider In Out Total $
claude-sonnet-4-5 anthropic 993 439 1432 0.009564
gpt-5.2 openai 1026 350 1376 0.006696
unverified OSINT claim 0% verification - uncertain Track 39 establishing Signal 75
Verification details 0% uncertain
Verification 0%: No corroborating evidence provided for Khan performing Hajj around May 27, 2026. The claim includes a pointed observation about Mecca's non-Muslim entry restrictions. Without travel reports, official statements, or credible media coverage in the check window, the core claim remains unverified.

No corroborating evidence provided for Khan performing Hajj around May 27, 2026. The claim includes a pointed observation about Mecca's non-Muslim entry restrictions. Without travel reports, official statements, or credible media coverage in the check window, the core claim remains unverified.

Evidence 0 AI 0 Track prior 50 4 resolved OSINT posts 25.0% false-positive/noise rate Source reliability 0 Bias balance 38 0 trusted sources
  • Trusted-source evidence score: 0.0
  • OSINT track record prior: 50.0
  • Checked window: 2026-05-27 13:50 through 2026-05-28 14:50.
  • AI evidence review score: 0.0
London Mayor Sadiq Khan, champion of London’s inclusivity, in Mecca performing Hajj.

Non-Muslims are forbidden from entering.
OSINT quality 65 59-70
Scored for discipline, source tier, information density, confidence signaling, coherence, and redundancy.
ChatGPT 59 Claude 70
  • Promotional/branded ad-like content is downranked by policy.
  • The statement that non-Muslims are forbidden from entering Mecca is broadly accurate, but the key factual claim—Khan being in Mecca performing Hajj—is not substantiated by the provided image and may rely on an unverified/possibly manipulated photo. The critique is clear and rhetorically effective, but the implied conclusion about inclusivity vs. religious site restrictions is more insinuation than argued inference.
  • Image shows the Kaaba and surrounding mosque area consistent with Mecca during Hajj/Umrah, which is relevant to the post’s claim about being in Mecca performing Hajj.
  • The person in the foreground could be anyone; the image alone does not reliably verify the identity as Sadiq Khan.
ChatGPT raw JSON 59
{
    "overall": 55,
    "content_type": "polemic",
    "rhetorical_intent": "critique",
    "dimensions": {
        "claim_honesty": 58,
        "logical_integrity": 55,
        "epistemic_transparency": 60,
        "communicative_effectiveness": 62,
        "grounding_adequacy": 70
    },
    "flags": [
        {
            "type": "identity_unverified",
            "text": "The image does not reliably verify the person is Sadiq Khan; it could be anyone and may be edited/composited."
        },
        {
            "type": "implied_hypocrisy_framing",
            "text": "Juxtaposes 'champion of inclusivity' with Mecca access rules to imply hypocrisy without explicitly arguing the connection."
        }
    ],
    "reasoning": "The statement that non-Muslims are forbidden from entering Mecca is broadly accurate, but the key factual claim—Khan being in Mecca performing Hajj—is not substantiated by the provided image and may rely on an unverified/possibly manipulated photo. The critique is clear and rhetorically effective, but the implied conclusion about inclusivity vs. religious site restrictions is more insinuation than argued inference."
}
Claude raw JSON 70
{
    "overall": 72,
    "content_type": "polemic",
    "rhetorical_intent": "challenge",
    "dimensions": {
        "claim_honesty": 65,
        "logical_integrity": 70,
        "epistemic_transparency": 60,
        "communicative_effectiveness": 90,
        "grounding_adequacy": 75
    },
    "flags": [
        {
            "type": "warning",
            "text": "Image assessment indicates possible manipulation/compositing with low authenticity score (0.42), undermining visual evidence for Khan's presence in Mecca"
        },
        {
            "type": "caution",
            "text": "Implicit hypocrisy claim (championing inclusivity while in exclusionary space) presented without explicit argument or acknowledgment of interpretive leap"
        },
        {
            "type": "info",
            "text": "Non-Muslim prohibition in Mecca is Tier 1 settled fact; no penalty for stating without evidence"
        }
    ],
    "reasoning": "The post makes a pointed juxtaposition between Khan's inclusivity advocacy and Mecca's access restrictions. The factual claim about non-Muslim prohibition is Tier 1 and accurate. However, the image evidence is questionable per the assessment's compositing concerns, and Khan's identity/presence is not reliably verified visually. The implied hypocrisy argument is never explicitly stated, reducing epistemic transparency. As a polemic, the punchy framing is appropriate and communicatively effective, but the reliance on potentially manipulated visual evidence and unstated logical connection between the two facts weakens claim honesty and grounding."
}
What we measure
0
$
Scoring calls: $0.016014
AI Score In Out Total ms $
ChatGPT 59 1353 229 1582 3635 0.005574
Claude 70 1485 399 1884 8759 0.010440
~ estimated where historical API usage was unavailable
Verification calls: $0.013716
AI Provider In Out Total $
claude-sonnet-4-5 anthropic 896 384 1280 0.008448
gpt-5.2 openai 938 259 1197 0.005268
Version 1.2 - 2026-05-20 17:30 ET