Group each usage example with its instruction, text, schema and output

README.md

@@ -65,26 +65,26 @@ Supply source text and a flat object JSON Schema with 1–8 required properties
 
 ## Verified source/schema/output examples
 
-These four observed examples are checked against the selected model and standalone runner. They demonstrate successes within a limited research scope; other requests can fail.
+Each example below is a complete walkthrough: **Prompt instruction + Source text + JSON Schema → Model output**. Open an example to see all four parts together.
 
-### Prompt instruction
+The instruction, source text and schema are the model's inputs. The model output is its observed response—not part of the prompt. These examples were verified with the released model; other requests can fail.
 
-The inference runner automatically includes this exact prompt instruction with every request:
+### Track and artist
 
-> Extract information from the supplied source_text according to the supplied JSON Schema. Return exactly one JSON object, with no explanation or Markdown. Copy values exactly, preserving case and spelling; do not normalize dates or numbers. Include every required key and no other keys. For string arrays, include all matching source spans in source order, or [] when absent. For nullable strings, use the exact source span or null when absent.
+<details open>
+<summary><strong>Example 1: Track and artist — prompt, source text, schema and output</strong></summary>
 
-The user message is the instruction, a blank line, then compact `{"source_text":<query>,"schema":<schema>}`. No expected answer is included.
+#### 1. Prompt instruction
 
-### Track and artist
+> Extract information from the supplied source_text according to the supplied JSON Schema. Return exactly one JSON object, with no explanation or Markdown. Copy values exactly, preserving case and spelling; do not normalize dates or numbers. Include every required key and no other keys. For string arrays, include all matching source spans in source order, or [] when absent. For nullable strings, use the exact source span or null when absent.
 
-Source text:
+#### 2. Source text
 
-```text
-Play the track Blue Lantern by Mira Sol.
-```
+> Play the track Blue Lantern by Mira Sol.
 
-<details>
-<summary>View JSON Schema</summary>
+#### 3. JSON Schema
+
+This defines the requested fields and their types.
 
 ```json
 {
@@ -121,29 +121,51 @@ Play the track Blue Lantern by Mira Sol.
 }
 ```
 
-</details>
+#### 4. Model output
 
-<details>
-<summary>View generated JSON</summary>
+The JSON below is generated by the model. It is shown here for reference and is not sent as an input.
 
 ```json
-{"track":["Blue Lantern"],"artist":["Mira Sol"],"album":[]}
+{
+  "track": [
+    "Blue Lantern"
+  ],
+  "artist": [
+    "Mira Sol"
+  ],
+  "album": []
+}
+```
+
+**Try this example locally:**
+
+```bash
+python inference.py --example 29
 ```
 
+This command supplies the instruction, source text and schema automatically.
+
 </details>
 
-Run: `python inference.py --example 29`.
+
+---
 
 ### Restaurant request
 
-Source text:
+<details>
+<summary><strong>Example 2: Restaurant request — prompt, source text, schema and output</strong></summary>
 
-```text
-Book River Moon in Denver for four people tomorrow.
-```
+#### 1. Prompt instruction
 
-<details>
-<summary>View JSON Schema</summary>
+> Extract information from the supplied source_text according to the supplied JSON Schema. Return exactly one JSON object, with no explanation or Markdown. Copy values exactly, preserving case and spelling; do not normalize dates or numbers. Include every required key and no other keys. For string arrays, include all matching source spans in source order, or [] when absent. For nullable strings, use the exact source span or null when absent.
+
+#### 2. Source text
+
+> Book River Moon in Denver for four people tomorrow.
+
+#### 3. JSON Schema
+
+This defines the requested fields and their types.
 
 ```json
 {
@@ -188,29 +210,56 @@ Book River Moon in Denver for four people tomorrow.
 }
 ```
 
-</details>
+#### 4. Model output
 
-<details>
-<summary>View generated JSON</summary>
+The JSON below is generated by the model. It is shown here for reference and is not sent as an input.
 
 ```json
-{"restaurant_name":["River Moon"],"city":["Denver"],"party_size_number":["four"],"timeRange":["tomorrow"]}
+{
+  "restaurant_name": [
+    "River Moon"
+  ],
+  "city": [
+    "Denver"
+  ],
+  "party_size_number": [
+    "four"
+  ],
+  "timeRange": [
+    "tomorrow"
+  ]
+}
 ```
 
+**Try this example locally:**
+
+```bash
+python inference.py --example 30
+```
+
+This command supplies the instruction, source text and schema automatically.
+
 </details>
 
-Run: `python inference.py --example 30`.
+
+---
 
 ### Multiple artists
 
-Source text:
+<details>
+<summary><strong>Example 3: Multiple artists — prompt, source text, schema and output</strong></summary>
 
-```text
-Play songs by Mira Sol and Theo Lane.
-```
+#### 1. Prompt instruction
 
-<details>
-<summary>View JSON Schema</summary>
+> Extract information from the supplied source_text according to the supplied JSON Schema. Return exactly one JSON object, with no explanation or Markdown. Copy values exactly, preserving case and spelling; do not normalize dates or numbers. Include every required key and no other keys. For string arrays, include all matching source spans in source order, or [] when absent. For nullable strings, use the exact source span or null when absent.
+
+#### 2. Source text
+
+> Play songs by Mira Sol and Theo Lane.
+
+#### 3. JSON Schema
+
+This defines the requested fields and their types.
 
 ```json
 {
@@ -239,29 +288,49 @@ Play songs by Mira Sol and Theo Lane.
 }
 ```
 
-</details>
+#### 4. Model output
 
-<details>
-<summary>View generated JSON</summary>
+The JSON below is generated by the model. It is shown here for reference and is not sent as an input.
 
 ```json
-{"artist":["Mira Sol","Theo Lane"],"album":[]}
+{
+  "artist": [
+    "Mira Sol",
+    "Theo Lane"
+  ],
+  "album": []
+}
+```
+
+**Try this example locally:**
+
+```bash
+python inference.py --example 35
 ```
 
+This command supplies the instruction, source text and schema automatically.
+
 </details>
 
-Run: `python inference.py --example 35`.
+
+---
 
 ### Nullable fields
 
-Source text:
+<details>
+<summary><strong>Example 4: Nullable fields — prompt, source text, schema and output</strong></summary>
 
-```text
-Play the last theme by Behzad Mirkhani.
-```
+#### 1. Prompt instruction
 
-<details>
-<summary>View JSON Schema</summary>
+> Extract information from the supplied source_text according to the supplied JSON Schema. Return exactly one JSON object, with no explanation or Markdown. Copy values exactly, preserving case and spelling; do not normalize dates or numbers. Include every required key and no other keys. For string arrays, include all matching source spans in source order, or [] when absent. For nullable strings, use the exact source span or null when absent.
+
+#### 2. Source text
+
+> Play the last theme by Behzad Mirkhani.
+
+#### 3. JSON Schema
+
+This defines the requested fields and their types.
 
 ```json
 {
@@ -299,18 +368,28 @@ Play the last theme by Behzad Mirkhani.
 }
 ```
 
-</details>
+#### 4. Model output
 
-<details>
-<summary>View generated JSON</summary>
+The JSON below is generated by the model. It is shown here for reference and is not sent as an input.
 
 ```json
-{"playlist":null,"music_item":"theme","service":null}
+{
+  "playlist": null,
+  "music_item": "theme",
+  "service": null
+}
 ```
 
+**Try this example locally:**
+
+```bash
+python inference.py --example 48
+```
+
+This command supplies the instruction, source text and schema automatically.
+
 </details>
 
-Run: `python inference.py --example 48`.
 
 ## Training
 

SHA256SUMS

@@ -4,7 +4,7 @@
 74a074f90bd5e7a26d5f6cd5757ddc1fbfcc72e259e0b23a210fa48d91b35fdb  JSONLITE_RESULTS.json
 c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4  LICENSE
 f53194e53a2af5ec857337e8213397ea4f81a7e02d2dbcf0384a00cf1cf7f76f  PACKAGING_VERIFICATION.json
-109004f107cec1aeefd8653b29194d344caca6891cff50cf0e75739438dd3bea  README.md
+e4904f5bfd95f87e67a8de6cb0874c397babef23c44a16ed53ec73e5480a5407  README.md
 5ee8f11f0e87becf1a29c44e2b0f3dacc2c779712b635558be57dd7ef44455d3  RUN_GUIDE.md
 c6191baf937bce61f1b747acfbcb975a17eef6e8a598682a751a1031d1cfee23  SOURCE_NOTICE.md
 6088771ab13fa1080c0ca0f31649deb9f417597d7c2055b0f388e86f41f2c415  TECHNICAL_REPORT.md