درس تطبيقي كامل

Platform column   API field
─────────────────────────────
Talker          → speaker
BeginTime       → start_time
FinishTime      → end_time
Utterance       → transcript
NoiseTag        → non_speech_events
Mood            → emotion
Show            (passed through unchanged)
Subject         (passed through unchanged)

const KEY_MAP = {
  Talker:    'speaker',
  BeginTime: 'start_time',
  FinishTime:'end_time',
  Utterance: 'transcript',
  NoiseTag:  'non_speech_events',
  Mood:      'emotion',
}

const adapt = row =>
  Object.fromEntries(
    Object.entries(row).map(([k, v]) => [KEY_MAP[k] ?? k, v])
  )

const originalAdapted = originalData.map(adapt)
const reworkedAdapted = reworkedData.map(adapt)

KEY_MAP = {
    "Talker":    "speaker",
    "BeginTime": "start_time",
    "FinishTime": "end_time",
    "Utterance": "transcript",
    "NoiseTag":  "non_speech_events",
    "Mood":      "emotion",
}

def adapt(row):
    return {KEY_MAP.get(k, k): v for k, v in row.items()}

original_adapted = [adapt(r) for r in original_data]
reworked_adapted = [adapt(r) for r in reworked_data]

[
  { "speaker": "Sarah Mitchell", "start_time": 0.00,  "end_time": 4.20,  "transcript": "Welcome to The Language Lab, the podcast where we break down how AI is changing the way we communicate.",                          "non_speech_events": "[intro jingle]", "emotion": "warm"       },
  { "speaker": "Sarah Mitchell", "start_time": 4.20,  "end_time": 8.00,  "transcript": "Today we have two fantastic guests joining us to talk about machine translation and quality assurance.",                             "non_speech_events": "",               "emotion": "enthusiastic" },
  { "speaker": "James Park",     "start_time": 8.00,  "end_time": 11.50, "transcript": "Thanks Sarah glad to be here I have been looking forward to this conversation for weeks.",                                           "non_speech_events": "",               "emotion": "friendly"   },
  { "speaker": "Elena Rossi",    "start_time": 11.50, "end_time": 15.00, "transcript": "Same here this is such an important topic right now especially with how fast the field is evolving.",                                 "non_speech_events": "",               "emotion": "engaged"    },
  { "speaker": "Sarah Mitchell", "start_time": 15.00, "end_time": 19.80, "transcript": "James lets start with you. Your team recently published a paper on neural machine translation for low resource languages.",           "non_speech_events": "",               "emotion": "curious"    },
  { "speaker": "James Park",     "start_time": 19.80, "end_time": 26.50, "transcript": "Yes so our main finding was that back translation combined with careful data augmentation can boost BLEU scores by up to twelve points for languages with under fifty thousand parallel sentences.", "non_speech_events": "", "emotion": "analytical" },
  { "speaker": "James Park",     "start_time": 26.50, "end_time": 30.00, "transcript": "The trick is selecting the right seed data and not just throwing everything at the model.",                                          "non_speech_events": "",               "emotion": "technical"  },
  { "speaker": "Elena Rossi",    "start_time": 30.00, "end_time": 34.50, "transcript": "That resonates with our work at the localization lab where we focus on Arabic dialect adaptation.",                                   "non_speech_events": "",               "emotion": "thoughtful" },
  { "speaker": "Elena Rossi",    "start_time": 34.50, "end_time": 39.00, "transcript": "Standard Arabic models completely fail when you feed them Tunisian or Moroccan dialect input.",                                       "non_speech_events": "",               "emotion": "concerned"  }
]

[
  { "speaker": "Sarah Mitchell", "start_time": 0.00,  "end_time": 4.20,  "transcript": "Welcome to The Language Lab, the podcast where we break down how AI is changing the way we communicate.",                 "non_speech_events": "[intro jingle]", "emotion": "warm"        },
  { "speaker": "Sarah Mitchell", "start_time": 4.20,  "end_time": 8.00,  "transcript": "Today, we have two fantastic guests joining us to talk about machine translation and quality assurance.",                  "non_speech_events": "",               "emotion": "enthusiastic" },
  { "speaker": "James Park",     "start_time": 8.00,  "end_time": 11.50, "transcript": "Thanks, Sarah. Glad to be here — I've been looking forward to this conversation for weeks.",                              "non_speech_events": "",               "emotion": "friendly"    },
  { "speaker": "Elena Rossi",    "start_time": 11.50, "end_time": 15.00, "transcript": "Same here. This is such an important topic right now, especially with how fast the field is evolving.",                    "non_speech_events": "",               "emotion": "engaged"     },
  { "speaker": "Sarah Mitchell", "start_time": 15.00, "end_time": 19.80, "transcript": "James, let's start with you. Your team recently published a paper on neural machine translation for low-resource languages.", "non_speech_events": "",               "emotion": "curious"     },
  { "speaker": "James Park",     "start_time": 19.80, "end_time": 23.20, "transcript": "Yes, so our main finding was that back-translation combined with careful data augmentation can boost BLEU scores by up to 12 points.", "non_speech_events": "", "emotion": "analytical"  },
  { "speaker": "James Park",     "start_time": 23.20, "end_time": 26.50, "transcript": "This holds for languages with under 50,000 parallel sentences.",                                                           "non_speech_events": "",               "emotion": "analytical"  },
  { "speaker": "James Park",     "start_time": 26.50, "end_time": 30.00, "transcript": "The trick is selecting the right seed data and not just throwing everything at the model.",                                "non_speech_events": "",               "emotion": "technical"   },
  { "speaker": "Elena Rossi",    "start_time": 30.00, "end_time": 39.00, "transcript": "That resonates with our work at the localization lab where we focus on Arabic dialect adaptation — standard Arabic models completely fail when you feed them Tunisian or Moroccan dialect input.", "non_speech_events": "", "emotion": "thoughtful" }
]

curl -X POST https://structural-diff-engine.onrender.com/v1/diff \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-request-id: batch-ep101-layer1-layer2-qa" \
  -d '{
    "original": <originalAdapted array>,
    "reworked": <reworkedAdapted array>
  }'

{
  "status": "success",
  "requestId": "batch-ep101-layer1-layer2-qa",
  "data": {
    "results": [
      { "status": "UNCHANGED", "notes": "exact match",          ... },  // row 0 — Sarah intro
      { "status": "MODIFIED",  "notes": "transcript changed",   ... },  // row 1 — comma added
      { "status": "MODIFIED",  "notes": "transcript changed",   ... },  // row 2 — James punctuation
      { "status": "MODIFIED",  "notes": "transcript changed",   ... },  // row 3 — Elena punctuation
      { "status": "MODIFIED",  "notes": "transcript changed",   ... },  // row 4 — Sarah question
      { "status": "SPLIT",     "notes": "split into 2 rows",    ... },  // row 5 — James finding (split)
      { "status": "UNCHANGED", "notes": "exact match",          ... },  // row 6 — James trick
      { "status": "MERGED",    "notes": "merged from 2 rows",   ... },  // rows 7+8 — Elena merged
      { "status": "MERGED",    "notes": "Source row 1/2 ...",   ... },  // ← trace entry, skip in counts
      { "status": "MERGED",    "notes": "Source row 2/2 ...",   ... }   // ← trace entry, skip in counts
    ],
    "scores": {
      "CER": 0.09,
      "WER": 0.14,
      "SER": 0.22,
      "cerT": 0.09,
      "werT": 0.14
    },
    "composite": {
      "score": 3.9,
      "grade": "B",
      "label": "Good"
    },
    "meta": {
      "originalRows": 9,
      "reworkedRows": 9
    }
  }
}