"you_get": { // HTTP 200 application/json after payment
"output_schema":
{
"type": "object",
"properties": {
"skill": {
"type": "string"
},
"verdict": {
"type": "string"
},
"classifier": {
"type": "object",
"properties": {
"verdict": {
"type": "string"
},
"probability_ai": {
"type": "number"
},
"threshold_ai": {
"type": "number"
},
"threshold_human": {
"type": "number"
},
"model_version": {
"type": "string"
},
"model_kind": {
"type": "string"
}
}
},
"content_type": {
"type": "string"
},
"possible_ai_influence": {
"type": "boolean"
},
"rubric_score": {
"type": "number"
},
"sections": {
"type": "array",
"items": {
"type": "object",
"properties": {
"section": {
"type": "string"
},
"section_weight": {
"type": "number"
},
"result": {
"type": "string"
},
"evidence": {
"type": "array"
}
}
}
},
"tell_phrases": {
"type": "array",
"items": {
"type": "object",
"properties": {
"phrase": {
"type": "string"
},
"tell_weight": {
"type": "number"
},
"count": {
"type": "integer"
}
}
}
},
"ai_likelihood": {
"type": "number"
},
"band": {
"type": "array",
"items": {
"type": "number"
}
},
"signals": {
"type": "object",
"properties": {
"sentence_length_mean": {
"type": "number"
},
"sentence_length_variance": {
"type": "number"
},
"burstiness": {
"type": "number"
},
"type_token_ratio": {
"type": "number"
},
"hapax_ratio": {
"type": "number"
},
"punctuation_diversity": {
"type": "integer"
},
"repeated_ngram_rate": {
"type": "number"
},
"stock_phrase_per_100": {
"type": "number"
},
"stock_phrase_hits": {
"type": "integer"
},
"stock_phrases_found": {
"type": "array",
"items": {
"type": "string"
}
},
"contraction_rate": {
"type": "number"
},
"average_word_length": {
"type": "number"
},
"line_length_uniformity": {
"type": "null"
},
"line_count": {
"type": "integer"
},
"verse_like": {
"type": "boolean"
},
"sentence_count": {
"type": "integer"
},
"lexical_features_used": {
"type": "boolean"
}
}
},
"method": {
"type": "string"
},
"word_count": {
"type": "integer"
},
"caveats": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"skill"
]
}
"example":
{
"skill": "ai_detector",
"verdict": "possible_ai_influence",
"classifier": {
"verdict": "uncertain",
"probability_ai": 0.362,
"threshold_ai": 0.585,
"threshold_human": 0.3233,
"model_version": "2026-10-13",
"model_kind": "logistic_regression"
},
"content_type": "opinion",
"possible_ai_influence": true,
"rubric_score": 0.4,
"sections": [
{
"section": "rhythm",
"section_weight": 0.1,
"result": "no_signal",
"evidence": [
"8 sentences, sentence-length CV 0.35 (AI <= 0.34, human >= 0.55)",
"rhythm is in the overlap range where human and prompted-AI text both sit"
]
},
{
"section": "vocabulary",
"section_weight": 0.4,
"result": "ai_sign",
"evidence": [
"tell-phrase weight 2.4 (2.64 per 100 words, 138-entry list)",
"tells: it's worth noting, a testament to, in conclusion",
"lexical diversity MTLD 105 (informational, not scored)",
"surprisal mean 3.21, variance 2.15, spike 0.40; rare-word share 0.033; MATTR 0.834; Zipf slope deviation 0.63",
"tell phrases are dense; possible AI influence (secondary signal)"
]
},
{
"section": "voice_structure",
"section_weight": 0.3,
"result": "no_signal",
"evidence": [
"ai cues: hedging (2 hedges)",
"human cues: none",
"first person, names, dialogue and sensory detail are not counted either way"
]
},
{
"section": "resolution",
"section_weight": 0.2,
"result": "no_signal",
"evidence": [
"rhythm vs vocabulary: no_overlap (no_signal / ai_sign)",
"vocabulary vs voice_structure: no_overlap (ai_sign / no_signal)",
"voice_structure vs rhythm: no_overlap (no_signal / no_signal)",
"tell phrases present but not confirmed by two sections; secondary signal only"
]
}
],
"tell_phrases": [
{
"phrase": "it's worth noting",
"tell_weight": 0.9,
"count": 1
},
{
"phrase": "a testament to",
"tell_weight": 0.9,
"count": 1
},
{
"phrase": "in conclusion",
"tell_weight": 0.6,
"count": 1
}
],
"ai_likelihood": 0.7822,
"band": [
0.5334,
1.0
],
"signals": {
"sentence_length_mean": 11.375,
"sentence_length_variance": 16.2344,
"burstiness": 0.3542,
"type_token_ratio": 0.7582,
"hapax_ratio": 0.8841,
"punctuation_diversity": 4,
"repeated_ngram_rate": 0.0,
"stock_phrase_per_100": 3.2967,
"stock_phrase_hits": 3,
"stock_phrases_found": [
"it's worth noting",
"a testament to",
"in conclusion"
],
"contraction_rate": 3.2967,
"average_word_length": 4.3846,
"line_length_uniformity": null,
"line_count": 1,
"verse_like": false,
"sentence_count": 8,
"lexical_features_used": true
},
"method": "stylometry",
"word_count": 91,
"caveats": [
"Detection is probabilistic and should not be used as the only evidence that a text was or was not written by a person.",
"ai_likelihood is a stylometric score from 0 to 1, not a calibrated probability. The band widens when there is less text and is not a statistical confidence interval.",
"A low score means these surface patterns are weak. It does not prove a person wrote the text.",
"Weights were chosen on a small set of public-domain prose, poems, and synthetic assistant-style paragraphs. Fixture accuracy is not a field accuracy."
]
}
},