{
  "snapshot_date": "2026-10-21",
  "scope": "Completed v5 versus curriculum-research experiment; separate architecture experiments excluded.",
  "standard_benchmark_or_leaderboard": false,
  "generation_sampling": {
    "temperature": 0.5,
    "top_k": 64,
    "top_p": 0.9,
    "image_seeds": [
      20261020,
      20261021
    ],
    "motion_seed": 20261021
  },
  "generation": {
    "source_v5": {
      "weights_sha256": "e20242e9971b6a7cef7ca23a65c25faa70a007807a55a2c0cfe35f4f5682a643",
      "photo_category_matches": 0,
      "photo_samples": 24,
      "novel_wording_matches": 0,
      "novel_wording_samples": 16,
      "motion_joint_matches": 1,
      "motion_samples": 16,
      "unseen_continuation_joint_matches": 0,
      "unseen_continuation_samples": 8
    },
    "joint_repair": {
      "weights_sha256": "de4846e5e63c0004cf0b6331127ab421d6843f6efde04243c6d5448ab4545240",
      "photo_category_matches": 23,
      "photo_samples": 24,
      "novel_wording_matches": 15,
      "novel_wording_samples": 16,
      "motion_joint_matches": 16,
      "motion_samples": 16,
      "unseen_continuation_joint_matches": 0,
      "unseen_continuation_samples": 8,
      "exact_training_photo_code_replays": 24,
      "exact_training_motion_code_replays": 16
    }
  },
  "retention": {
    "eval_batches_per_task": 4,
    "batch_sha256": "bfa74f2ea9c7c814894160693a11857cf5fba9971e6e3b70617d857e8c3e2944",
    "phases": {
      "source_v5": {
        "weights_sha256": "e20242e9971b6a7cef7ca23a65c25faa70a007807a55a2c0cfe35f4f5682a643",
        "losses": {
          "text": 3.948372427367484,
          "chat_text": 1.6765498408440793,
          "coding": 1.7610283871588197,
          "t2i": 8.717013671945807,
          "i2t": 2.509420299240159,
          "t2v": 5.122131407260895,
          "v2t": 0.8410091984505746,
          "vcont": 6.256978213787079,
          "tools": 0.4623708201062148,
          "t2m": 6.144639953858572,
          "m2t": 3.6306305448963956,
          "t2a": 9.011601033198106,
          "a2t": 3.88449745137116
        },
        "parameters": 90247794
      },
      "joint_repair": {
        "weights_sha256": "de4846e5e63c0004cf0b6331127ab421d6843f6efde04243c6d5448ab4545240",
        "losses": {
          "text": 4.418278653778919,
          "chat_text": 2.070340123627516,
          "coding": 2.2605253159999847,
          "t2i": 11.670267707399868,
          "i2t": 2.727402084141879,
          "t2v": 6.736757338047028,
          "v2t": 1.6935838811537798,
          "vcont": 8.68588125705719,
          "tools": 0.804386016036801,
          "t2m": 6.04225613219775,
          "m2t": 4.89992640153417,
          "t2a": 8.555012301572333,
          "a2t": 4.078481768739635
        },
        "parameters": 90247794
      }
    }
  },
  "production_promoted": false,
  "research_session": {
    "elapsed_seconds": 5729.144976377487,
    "optimizer_input_tokens": 20971520,
    "optimizer_steps": 5120,
    "prior_tasks_regressed": 11,
    "prior_tasks_probed": 13
  },
  "research_supervised_targets": 10005264,
  "research_shared_ancestry_added_inputs": 6291456,
  "notes": [
    "Photo/clip matches are narrow recall probes.",
    "Successful research outputs reproduce training visual-token sequences.",
    "Four held-out batches/task are a small paired screen, not a full semantic evaluation."
  ]
}