{
  "schema": "br-voice-reasoner-training-manifest.v2",
  "model": {
    "name": "BR-Voice-Reasoner",
    "release_checkpoint": 2318,
    "format": "merged_full_weights",
    "dtype": "bfloat16",
    "weight_shards": 16
  },
  "base_model": {
    "hub_id": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
    "config_sha256": "e6f8c637528461398ef4e11d48b6112ce73db2458a563dfea548127c2cce253f",
    "index_sha256": "13ae0b6fa947acd1ec5e163d493884724999788752b699266eb09b14ba914c90"
  },
  "training": {
    "method": "OPSD fixed-teacher on-policy distillation",
    "student_initialization": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
    "teacher": {
      "checkpoint": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
      "frozen": true,
      "input_view": "transcript or text form of the same user request with multimodal fields removed",
      "target_answer_available": false
    },
    "steps": 2318,
    "epochs": 2,
    "global_batch_size": 16,
    "learning_rate": 5e-6,
    "projector_learning_rate": 1e-5,
    "minimum_learning_rate": 5e-7,
    "learning_rate_schedule": "cosine",
    "warmup_fraction": 0.03,
    "seed": 20260819,
    "loss": {
      "beta": 0.5,
      "lambda": 1.0,
      "sft_alpha": 0.0,
      "temperature": 1.2,
      "teacher_logits_topk": 128
    },
    "rollout": {
      "source": "student on-policy",
      "thinking": true,
      "maximum_completion_tokens": 2048
    },
    "trainable_modules": [
      "thinker.audio_tower.proj1",
      "thinker.audio_tower.proj2"
    ],
    "frozen_components": "all other language-model, audio-encoder, and vision-encoder weights",
    "capability_retention_mechanism": "parameter isolation",
    "optimization_scope_note": "Text-only rows do not update the trainable audio projection modules and are not claimed as a capability-retention mechanism."
  },
  "training_population": {
    "rows": 32965,
    "audio_rows": 25454,
    "text_only_rows": 7511,
    "source_order": "fixed V6-ad order",
    "expanded_or_filtered": false,
    "branches": {
      "ifeval": 6675,
      "mmsu": 6844,
      "retention_instruction_following": 615,
      "retention_knowledge_mcq": 1590,
      "retention_open_response": 3696,
      "retention_reasoning": 968,
      "retention_safety_alignment": 642,
      "sdqa": 11935
    },
    "prompt_only_data_sha256": "d32549b279697d72964e167466b297d67f1ac3de84a728d285d92c09bbc034a8",
    "provenance_sha256": "88e89b8905f0f89c5d1fd3b1915fc6e5d58416277f7da48c59a08ff19065145e"
  },
  "merge": {
    "adapter_checkpoint_sha256": "6bb566463abf4d44730779a4cb8231fc39b733a7aba48f4d29971deecb3d95e7",
    "replacement_semantics": "complete_parameter_replacement",
    "compute_dtype": "float32",
    "output_dtype": "preserve_base_tensor_dtype",
    "changed_parameters": [
      "thinker.audio_tower.proj1.bias",
      "thinker.audio_tower.proj1.weight",
      "thinker.audio_tower.proj2.bias",
      "thinker.audio_tower.proj2.weight"
    ],
    "lora_delta_parameters": 0
  },
  "evaluation": {
    "date_utc": "2026-09-02",
    "benchmark": "VoiceBench",
    "protocol_file": "evaluation_protocol.json",
    "empty_generation_recovery": {
      "evaluated_samples": 7783,
      "samples_entering_seed_fallback": 5,
      "samples_recovered": 4,
      "samples_exhausted_and_counted_incorrect": 1,
      "selection": "first non-empty result; no ranking or best-of selection"
    },
    "model_judge": {
      "model": "openai/gpt-4o-mini",
      "model_kind": "alias",
      "accessed_utc": "2026-09-02",
      "gateway": "OpenRouter",
      "upstream_provider_only": "OpenAI",
      "judgments_per_sample": 3
    },
    "nine_subset_mean": 90.4613,
    "non_sdqa_eight_subset_mean": 92.4787,
    "sdqa_gpt4o_mini_majority": {
      "score": 74.3219,
      "correct": 411,
      "total": 553,
      "votes": 3
    },
    "mmsu": {
      "score": 85.6539,
      "correct": 2633,
      "total": 3074
    }
  }
}