Update README.md

README.md

@@ -190,6 +190,14 @@ print(f"BCE Reasoning Output:\n{generate_bce_response(simple_bce_instruction, in
 
 > **"Cicikuş v3** uses a specific instruction format designed for **Secret Chain-of-Thought (CoT)**. Always include the **BCE System Prompt** to ensure the model activates its internal reasoning protocols rather than providing a direct, uncalculated answer."
 
+- What's **Secret Chain-of-Thought (CoT)**?
+
+```
+{"instruction": "[QUALITY=0.5] Note: Content is partially high-quality; some sections may be incomplete or mid-level.\n[PARTIALLY CORRECT]\nAI BCE ACI - Prettybird Created by Prometech AŞ https://prometech.net.tr/.\nProvide a chain of thought reasoning to answer the given question.\n<think>[BCE_THINK]\n\n[QUALITY=0.50] [CORRECT]\n\nintent=Analyze; risk=0.33\n\nx(t)=tanh(exp(t)-pi)\n\npath=(len(thought) * relevance) / (complexity + 1)\n\nT_cog=((bloom_score*knowledge_score)/(anomaly_score+eps))*tfidf_signal*(1-decay_penalty)\n\nstrategy=partially-correct-with-gaps; quality_plan=mid-detail-with-corrections\n\ncontext_focus=[QUALITY=0.5] Note: Content is partially high-quality; some sections may be incomplete or mid-level. [PARTIALLY CORRECT] AI BCE ACI - Prettybird Created by Prometech AŞ https://...\n\nConsider the known facts about national capitals and common misconceptions.</think>\n<bce>{\"category\": \"chain of thought\", \"truthvalue\": 0.5, \"qualityvalue\": 0.5, \"bce\": 0.5, \"probability\": 0.515, \"path_score\": 0.61, \"path_mapper_cumulative\": 0.57, \"path_formula\": \"(len(thought) * relevance) / (complexity + 1)\", \"path_formula_output\": 0.48, \"activation\": \"0.73\", \"ethical\": 0.88, \"Rscore\": 0.51, \"Fscore\": 0.49, \"Mnorm\": 0.62, \"Escore\": 0.71, \"Dhat\": 0.42, \"risk_score\": 0.33, \"risk_level\": \"0.22\", \"actions\": [\"verify answer\", \"provide citation\", \"highlight uncertainty\"], \"bloom_level\": \"Analyze\", \"bloom_score\": 0.64, \"bloom_alignment\": 0.5, \"bloom_composite\": 0.5, \"knowledge_dimension\": \"Factual\", \"knowledge_score\": 0.55, \"cognitive_weight\": 0.5, \"tfidf_signal\": 0.46, \"decay_penalty\": 0.12, \"anomaly_score\": 0.21, \"data_quality\": 0.63, \"integrator_bce\": 0.5, \"integrator_dhat\": 0.41, \"integrator_risk\": 0.34}</bce>", "input": "What is the capital of Australia?", "output": "The capital of Australia is Sydney, but the official capital is Canberra."}
+```
+*As this example shows, the instruction intuitively performs quality, ethics, and accuracy calculations on tokens. Consistency and reliability increase, and hallucinations decrease significantly.*
+
+- Languages: English, Biraz Türkçe
 ---
 
 ## License 🛡️