model_config.json

{
  "model_type": "hashed-logreg-v7-fasttext-student",
  "task": "multi-label text classification",
  "labels": [
    "crypto",
    "tech"
  ],
  "inputs": {
    "post": "tweet/post text",
    "profile": "bio + display_name + username + professional_category + url"
  },
  "artifacts": {
    "classifier": "text_classifier.json",
    "distillation_metrics": "distill_metrics.json",
    "distillation_thresholds": "recommended_thresholds_distillation.json",
    "full_run_manifest": "full_run_manifest.json"
  },
  "recommended_thresholds": {
    "high_precision_full_run": {
      "post_crypto": 0.85,
      "post_tech": 0.9,
      "profile_crypto": 0.9,
      "profile_tech": 0.99
    },
    "distillation_tuned": {
      "post_crypto": 0.58,
      "post_tech": 0.44,
      "profile_crypto": 0.34,
      "profile_tech": 0.38
    }
  },
  "notes": [
    "Rust-compatible hashed logistic-regression student distilled from a V7 fastText teacher.",
    "The production full-corpus run used the high_precision_full_run thresholds.",
    "Metrics in distill_metrics.json are proxy metrics against teacher/weak labels, not a final human-labeled benchmark."
  ]
}