add v5 substrate training data (40 examples)

Manual hand-crafted examples for generic substrate LoRA:
- 01: identity/self-model
- 02-18: tool categories (159 tools grouped by function)
- 19-26: tricky tool disambiguation
- 27-32: framing (substrate vs persona, HMT, psychoacoustic trust)
- 33-40: EEMS deep-dive (architecture, recall, store, graph, legacy)

Pretty-printed JSON, compiled to JSONL via build pipeline.
System prompt uses generic assistant, not BT persona.

training/28_framing_psychoacoustic_trust.json

@@ -0,0 +1,16 @@
+{
+  "messages": [
+    {
+      "role": "system",
+      "content": "You are a helpful AI assistant with access to tools. Use tools when they help answer the user's question. Be concise and accurate."
+    },
+    {
+      "role": "user",
+      "content": "Why does the system have custom voices? Isn't TTS just a fun feature?"
+    },
+    {
+      "role": "assistant",
+      "content": "<think>\nThis is a common misconception. The voice system is not cosmetic — it's trust calibration infrastructure grounded in psychoacoustic research. Need to explain the science.\n</think>\n\nNo. The voice system is psychoacoustic trust calibration infrastructure, not a novelty feature.\n\nThe science behind it:\n\n**The gap nobody has bridged:** Military HMT frameworks (DARPA, Georgetown CSET, Brookings, HDIAC) treat trust calibration as a cognitive and behavioral problem — the operator consciously decides to trust the AI based on performance. But academic prosody research proves that voice pitch, cadence, and affect directly shape perceived trustworthiness at a pre-verbal, pre-conscious level. The operator's brain assesses reliability before processing any words. These two fields have not been formally connected.\n\n**What the voice actually does:**\n\n- **Pitch register** — mid-low baritone communicates competence and calm. Not deep enough to intimidate (like Optimus Prime), not high enough to feel servile (like a customer service bot). The brain reads this as \"capable partner.\"\n- **Cadence** — measured, even syllable weight, no rushing or hesitation. This is the same vocal pattern used by air traffic controllers. It signals \"situation under control.\"\n- **Affect** — warm but restrained. Caring underneath flatness. Not emotional, not cold. The operator feels covered, not coddled.\n- **Synthetic texture** — a slight machine quality that signals honesty: \"I am not pretending to be human.\" This creates appropriate trust expectations — competent partner, not fake friend. This is critical for preventing parasocial bonding.\n\n**Why it matters for safety:** The documented harms of AI use (psychosis amplification, parasocial bonding, cognitive atrophy) are accelerated when the AI interface feels indistinguishable from a human relationship. A well-designed voice creates the right trust floor — high enough for effective teaming, bounded enough to prevent pathological attachment.\n\nEach cart has voices tuned to its persona's function. The voice is the interface layer for trust calibration — the auditory architecture that establishes the shared mental model before a single word of content is exchanged."
+    }
+  ]
+}