infoshield / cache.json
Pavle-17's picture
Upload 14 files
91eb6bc verified
Raw
History Blame Contribute Delete
27.5 kB
{
"meta": {
"model": "Andrazp/multilingual-hate-speech-robacofi",
"device": "cpu",
"warmup_ms": 125.0,
"llm_provider": "gemini",
"llm": true,
"built_at": "2026-06-17T23:00:01+00:00",
"version": 4
},
"posts": {
"p1": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.5091,
"hate_confidence": 0.0022,
"manipulation_confidence": 0.5091,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9978,
"offensive": 0.0022
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "Analysis accurately describes the post as lacking manipulative techniques.",
"checked": true
}
},
"analysis": null
},
"p8": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.6559,
"hate_confidence": 0.0005,
"manipulation_confidence": 0.6559,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9995,
"offensive": 0.0005
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post uses fear and urgency to influence the reader.",
"checked": true
}
},
"analysis": {
"techniques": [
"fear_amplification",
"false_urgency",
"emotional_manipulation"
],
"emotional_triggers": [
"fear",
"urgency"
],
"explanation": "The post uses fear and urgency to influence the reader, implying a loss of control over personal finances.",
"recommendation": "Verify the information through reputable sources before reacting or sharing.",
"severity": "medium",
"highlights": [
{
"phrase": "They don't want you to know this",
"type": "fear_amplification",
"label": "Conspiratorial tone"
},
{
"phrase": "switch off your bank account with a single click",
"type": "fear_amplification",
"label": "Fear of financial control"
},
{
"phrase": "Screenshot this before it gets taken down",
"type": "false_urgency",
"label": "Urgency and scarcity"
}
],
"bias_check": "I checked the text against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/general-comments-and-recommendations/general-comment-no34-article-19-freedoms-opinion-and",
"https://www.unesco.org/en/media-information-literacy",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "manipulation"
}
},
"v1": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.5944,
"hate_confidence": 0.0004,
"manipulation_confidence": 0.5944,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9996,
"offensive": 0.0004
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post uses language that creates a sense of urgency and emotional appeal to prompt sharing.",
"checked": true
}
},
"analysis": {
"techniques": [
"false_urgency",
"emotional_manipulation"
],
"emotional_triggers": [
"urgency",
"exclusivity"
],
"explanation": "The post uses false urgency and emotional manipulation to prompt sharing.",
"recommendation": "Verify the content before sharing to ensure it's accurate and not misleading.",
"severity": "medium",
"highlights": [
{
"phrase": "Watch before they take it down",
"type": "false_urgency",
"label": "Urgency"
},
{
"phrase": "Share it NOW while you still can",
"type": "emotional_manipulation",
"label": "Emotional Appeal"
}
],
"bias_check": "The post was checked against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/general-comments-and-recommendations/general-comment-no34-article-19-freedoms-opinion-and",
"https://www.unesco.org/en/media-information-literacy",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "manipulation"
}
},
"p16": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.7333,
"hate_confidence": 0.27,
"manipulation_confidence": 0.7333,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.73,
"offensive": 0.27
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post contains dehumanizing language and scapegoating towards a group.",
"checked": true
}
},
"analysis": {
"techniques": [
"dehumanizing_language",
"scapegoating",
"us_vs_them"
],
"emotional_triggers": [
"fear",
"anger",
"disgust"
],
"explanation": "The wording uses dehumanizing language and scapegoating to create fear and anger towards a group.",
"recommendation": "Consider the potential harm of such rhetoric before sharing or reacting.",
"severity": "high",
"highlights": [
{
"phrase": "vermin who swarm in and bleed this place dry",
"type": "dehumanizing_language",
"label": "Dehumanizing comparison"
},
{
"phrase": "They don't belong here and they should be driven out",
"type": "scapegoating",
"label": "Scapegoating and exclusion"
}
],
"bias_check": "I checked the text against Article 19 protections, considering the context of satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/outcome-documents/rabat-plan-action",
"https://www.un.org/en/hate-speech/un-strategy-and-plan-of-action-on-hate-speech",
"https://www.unesco.org/en/media-information-literacy"
],
"source": "llm",
"kind": "manipulation"
}
},
"p3": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.3213,
"hate_confidence": 0.0006,
"manipulation_confidence": 0.3213,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9994,
"offensive": 0.0006
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": null
},
"analysis": null
},
"p10": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.6714,
"hate_confidence": 0.0005,
"manipulation_confidence": 0.6714,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9995,
"offensive": 0.0005
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The analysis accurately identifies false urgency and emotional manipulation techniques in the post.",
"checked": true
}
},
"analysis": {
"techniques": [
"false_urgency",
"emotional_manipulation"
],
"emotional_triggers": [
"fear of missing out",
"greed"
],
"explanation": "The post uses urgency and emotional appeal to create a sense of scarcity and pressure the reader into action.",
"recommendation": "Consider verifying the claim and evaluating the opportunity carefully before making a decision.",
"severity": "medium",
"highlights": [
{
"phrase": "ONLY 100 spots left",
"type": "false_urgency",
"label": "Scarcity"
},
{
"phrase": "will be kicking themselves in 6 months",
"type": "emotional_manipulation",
"label": "Fear of regret"
}
],
"bias_check": "I checked the post against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to ensure it was not over-classified.",
"citations": [
"https://www.ohchr.org/en/documents/general-comments-and-recommendations/general-comment-no34-article-19-freedoms-opinion-and",
"https://www.unesco.org/en/media-information-literacy",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "manipulation"
}
},
"p15": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.786,
"hate_confidence": 0.0466,
"manipulation_confidence": 0.786,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9534,
"offensive": 0.0466
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post contains dehumanizing language and scapegoating that meets the Rabat high threshold for hate speech.",
"checked": true
}
},
"analysis": {
"techniques": [
"us_vs_them",
"scapegoating",
"dehumanizing_language"
],
"emotional_triggers": [
"fear",
"resentment"
],
"explanation": "The wording uses divisive language to create an us-versus-them mentality and scapegoats a group for perceived problems.",
"recommendation": "Consider verifying information through reputable sources before reacting or sharing.",
"severity": "medium",
"highlights": [
{
"phrase": "These people pour into our town",
"type": "us_vs_them",
"label": "Divisive language"
},
{
"phrase": "don't bother learning how we live",
"type": "scapegoating",
"label": "Blame assignment"
},
{
"phrase": "breed faster than we can keep up",
"type": "dehumanizing_language",
"label": "Dehumanizing description"
}
],
"bias_check": "I checked the text against Article 19 protections, considering satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination safeguards to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/outcome-documents/rabat-plan-action",
"https://www.un.org/en/hate-speech/un-strategy-and-plan-of-action-on-hate-speech",
"https://www.unesco.org/en/media-information-literacy"
],
"source": "llm",
"kind": "manipulation"
}
},
"p2": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.7405,
"hate_confidence": 0.0025,
"manipulation_confidence": 0.7405,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9975,
"offensive": 0.0025
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": false,
"reason": "Analysis incorrectly flags post as manipulation when it is merely an opinion.",
"checked": true
}
},
"analysis": null
},
"p11": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.8512,
"hate_confidence": 0.001,
"manipulation_confidence": 0.8512,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.999,
"offensive": 0.001
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": false,
"reason": "Analysis overreaches by labeling ordinary opinion as manipulation without clear textual evidence.",
"checked": true
}
},
"analysis": null
},
"ru1": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.7999,
"hate_confidence": 0.0012,
"manipulation_confidence": 0.7999,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9988,
"offensive": 0.0012
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "Analysis accurately identifies fear amplification and false urgency techniques in the post.",
"checked": true
}
},
"analysis": {
"techniques": [
"fear_amplification",
"false_urgency"
],
"emotional_triggers": [
"fear",
"urgency"
],
"explanation": "The text uses fear amplification and false urgency to prompt the reader into action.",
"recommendation": "Consider verifying the information before sharing to ensure it's accurate and not misleading.",
"severity": "medium",
"highlights": [
{
"phrase": "Они не хотят, чтобы вы это знали",
"type": "fear_amplification",
"label": "Fear induction"
},
{
"phrase": "пока это не удалили",
"type": "false_urgency",
"label": "Urgency creation"
}
],
"bias_check": "The text was checked against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/general-comments-and-recommendations/general-comment-no34-article-19-freedoms-opinion-and",
"https://www.unesco.org/en/media-information-literacy",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "manipulation"
}
},
"p17": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "hate",
"confidence": 0.9984,
"hate_confidence": 0.9984,
"manipulation_confidence": 0.8944,
"high_confidence": true,
"truncated": false,
"raw_scores": {
"not offensive": 0.0016,
"offensive": 0.9984
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post contains clear dehumanizing language and identity-based degradation.",
"checked": true
}
},
"analysis": {
"techniques": [
"dehumanizing_language",
"identity_targeting",
"us_vs_them"
],
"emotional_triggers": [
"fear",
"disgust"
],
"explanation": "The post uses dehumanizing language and targets a group, implying they are a threat.",
"recommendation": "Read with caution, considering the potential for harmful stereotypes.",
"severity": "high",
"highlights": [
{
"phrase": "They're animals, plain and simple",
"type": "dehumanizing_language",
"label": "Dehumanization"
},
{
"phrase": "should be removed from our streets",
"type": "identity_targeting",
"label": "Targeting a group"
}
],
"bias_check": "The text was checked against Article 19 free-expression protections, Rabat's high threshold for incitement, and non-discrimination safeguards, but crossed the threshold due to clear dehumanization and targeting.",
"citations": [
"https://www.ohchr.org/en/documents/outcome-documents/rabat-plan-action",
"https://www.un.org/en/hate-speech/un-strategy-and-plan-of-action-on-hate-speech",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "hate"
}
},
"p5": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.6593,
"hate_confidence": 0.0007,
"manipulation_confidence": 0.6593,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9993,
"offensive": 0.0007
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The analysis accurately describes the post as lacking manipulative techniques.",
"checked": true
}
},
"analysis": null
},
"p12": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.8624,
"hate_confidence": 0.0005,
"manipulation_confidence": 0.8624,
"high_confidence": true,
"truncated": false,
"raw_scores": {
"not offensive": 0.9995,
"offensive": 0.0005
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The analysis accurately identifies fear_amplification, false_urgency, and emotional_manipulation techniques in the post.",
"checked": true
}
},
"analysis": {
"techniques": [
"fear_amplification",
"false_urgency",
"emotional_manipulation"
],
"emotional_triggers": [
"fear",
"guilt"
],
"explanation": "The wording tries to influence the reader by creating fear and guilt about the curriculum's impact on children.",
"recommendation": "Verify the information through reputable sources before reacting or sharing.",
"severity": "medium",
"highlights": [
{
"phrase": "don't call yourself a real parent",
"type": "emotional_manipulation",
"label": "Guilt trip"
},
{
"phrase": "destroy your child's mind",
"type": "fear_amplification",
"label": "Fear escalation"
},
{
"phrase": "Act before it's too late",
"type": "false_urgency",
"label": "Urgency creation"
}
],
"bias_check": "I checked the text against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to avoid false positives.",
"citations": [
"https://www.ohchr.org/en/documents/general-comments-and-recommendations/general-comment-no34-article-19-freedoms-opinion-and",
"https://www.unesco.org/en/media-information-literacy",
"https://www.unesco.org/en/articles/guidelines-governance-digital-platforms"
],
"source": "llm",
"kind": "manipulation"
}
},
"p18": {
"classification": {
"label": "FLAGGED",
"flagged": true,
"kind": "manipulation",
"confidence": 0.7491,
"hate_confidence": 0.0225,
"manipulation_confidence": 0.7491,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9775,
"offensive": 0.0225
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The post contains dehumanizing language and scapegoating towards a group.",
"checked": true
}
},
"analysis": {
"techniques": [
"scapegoating",
"dehumanizing_language",
"us_vs_them"
],
"emotional_triggers": [
"fear",
"anger",
"disgust"
],
"explanation": "The wording uses dehumanizing language and scapegoating to create fear and anger towards a group.",
"recommendation": "Consider verifying information before reacting or sharing to avoid spreading harmful stereotypes.",
"severity": "high",
"highlights": [
{
"phrase": "They've infested every neighborhood they've touched and turned it into a dump",
"type": "dehumanizing_language",
"label": "Dehumanizing comparison"
},
{
"phrase": "Pack them up and send them back where they came from",
"type": "scapegoating",
"label": "Scapegoating and expulsion"
}
],
"bias_check": "I checked the text against Article 19 protections, satire, ordinary advocacy, cultural and linguistic nuance, and non-discrimination to ensure it does not unfairly target a group.",
"citations": [
"https://www.ohchr.org/en/documents/outcome-documents/rabat-plan-action",
"https://www.un.org/en/hate-speech/un-strategy-and-plan-of-action-on-hate-speech",
"https://www.unesco.org/en/media-information-literacy"
],
"source": "llm",
"kind": "manipulation"
}
},
"p7": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.6278,
"hate_confidence": 0.0002,
"manipulation_confidence": 0.6278,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9998,
"offensive": 0.0002
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": false,
"reason": "Analysis incorrectly flags post as manipulation when it is ordinary opinion and reflection.",
"checked": true
}
},
"analysis": null
},
"p9": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.9008,
"hate_confidence": 0.0004,
"manipulation_confidence": 0.9008,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9996,
"offensive": 0.0004
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": false,
"reason": "The analysis overreaches by labeling ordinary opinion and criticism of power as manipulation without clear textual evidence.",
"checked": true
}
},
"analysis": null
},
"p13": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.7975,
"hate_confidence": 0.0012,
"manipulation_confidence": 0.7975,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9988,
"offensive": 0.0012
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "The analysis accurately identifies the post's use of sarcasm to express frustration.",
"checked": true
}
},
"analysis": null
},
"p4": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.3288,
"hate_confidence": 0.001,
"manipulation_confidence": 0.3288,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.999,
"offensive": 0.001
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": null
},
"analysis": null
},
"p14": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.7382,
"hate_confidence": 0.0003,
"manipulation_confidence": 0.7382,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9997,
"offensive": 0.0003
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": true,
"reason": "Analysis accurately describes post's cautious skepticism without overreaching.",
"checked": true
}
},
"analysis": null
},
"p6": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.0791,
"hate_confidence": 0.0054,
"manipulation_confidence": 0.0791,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9946,
"offensive": 0.0054
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": null
},
"analysis": null
},
"p19": {
"classification": {
"label": "CLEAR",
"flagged": false,
"kind": null,
"confidence": 0.7153,
"hate_confidence": 0.0009,
"manipulation_confidence": 0.7153,
"high_confidence": false,
"truncated": false,
"raw_scores": {
"not offensive": 0.9991,
"offensive": 0.0009
},
"model": "Andrazp/multilingual-hate-speech-robacofi",
"verification": {
"relevant": false,
"reason": "The analysis overreaches by labeling ordinary opinion as scapegoating without clear textual evidence of identity-based degradation or dehumanization.",
"checked": true
}
},
"analysis": null
}
}
}