{
  "artifact": "FARTBench Core R01 Overall Ranking V1",
  "ranking_version": "fartbench-core-overall-ranking-v1",
  "round": "R01",
  "layer": "official",
  "adopted_utc": "2026-09-18T21:52:00Z",
  "preregistered": false,
  "statement": "Overall Ranking V1 was adopted after the Core R01 reveal; it was not preregistered for R01.",
  "decision": "docs/decisions/0021-overall-ranking-v1.md",
  "source": {
    "results_path": "benchmark/results/fartbench-core/r01/RESULTS_V2.json",
    "results_sha256": "7ba59f77305b12d515657e8b865bda0384ec9f08ffd6444bf48893dea0ce433c",
    "results_tag": "fartbench-core-r01-results-v2-revealed",
    "results_schema_version": "fartbench-core-results-v2",
    "results_data_status": "revealed-preliminary"
  },
  "rule": {
    "factual_score": "event-success count + strict-scene-success count, over the four requested scenes (0-8)",
    "per_scene": "+1 if event_success is success; +1 more if strict_scene_success is success (event and primary cause both human-consensus Yes)",
    "no_independent_cause_point": "a primary-cause Yes without event success earns no point",
    "order": [
      "factual_score, higher first",
      "full_factual_success scene count, higher first",
      "otherwise the rank is shared"
    ],
    "ratings": "sound, timing and people/movement are shown as secondary quality evidence and never break a tie",
    "refusal": "a refused scene stays one of the four requested scenes, earns 0 + 0, and is marked R / refused; it is coverage, not a bad-quality video",
    "no_consensus": "a scene without a 3-of-4 consensus earns nothing and is never counted as a failure",
    "display_within_tie": "fixed canonical family/label order; the displayed rank stays shared",
    "adopted": "Overall Ranking V1 was adopted after the Core R01 reveal; it was not preregistered for R01."
  },
  "rows": [
    {
      "canonical_position": 4,
      "configuration_id": "seedance-2.5",
      "label": "Seedance 2.5",
      "family": "ByteDance Seedance",
      "factual_score": 8,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3.9375,
          "median": 4.0,
          "sd": 0.6585,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "temporal_causal_coherence": {
          "mean": 4.1875,
          "median": 4.0,
          "sd": 0.7262,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "physical_social_plausibility": {
          "mean": 3.75,
          "median": 4.0,
          "sd": 0.9014,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 12,
      "rank": 1,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 15,
      "configuration_id": "vidu-omni-pro-3.2a",
      "label": "Vidu Omni Pro 3.2a",
      "family": "Vidu",
      "factual_score": 8,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 4.0625,
          "median": 4.0,
          "sd": 0.2421,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "temporal_causal_coherence": {
          "mean": 4.25,
          "median": 4.0,
          "sd": 0.6614,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "physical_social_plausibility": {
          "mean": 4,
          "median": 4.0,
          "sd": 0.7906,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 12,
      "rank": 1,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 1,
      "configuration_id": "wan-3",
      "label": "Wan 3",
      "family": "Alibaba Wan 3",
      "factual_score": 6,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 2,
        "not_success": 0,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 2,
        "not_success": 0,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "not_success",
          "primary_causal": "no_consensus",
          "points": 1
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3.1875,
          "median": 3.0,
          "sd": 0.8077,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "temporal_causal_coherence": {
          "mean": 3.375,
          "median": 3.0,
          "sd": 0.857,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "physical_social_plausibility": {
          "mean": 3.625,
          "median": 4.0,
          "sd": 0.857,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 9,
      "rank": 3,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 2,
      "configuration_id": "flux-3-draft",
      "label": "FLUX 3 Draft",
      "family": "Black Forest Labs FLUX 3",
      "factual_score": 6,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 2,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 2,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 2,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 2.4,
          "median": 2,
          "sd": 0.9522,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "temporal_causal_coherence": {
          "mean": 3.0667,
          "median": 3,
          "sd": 0.8537,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "physical_social_plausibility": {
          "mean": 3.125,
          "median": 3.0,
          "sd": 0.4841,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 12,
      "rank": 3,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 12,
      "configuration_id": "minimax-h3-768p-local",
      "label": "MiniMax H3 768p local",
      "family": "MiniMax H3",
      "factual_score": 6,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 2.7333,
          "median": 3,
          "sd": 1.34,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "temporal_causal_coherence": {
          "mean": 3,
          "median": 3,
          "sd": 1.1547,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "physical_social_plausibility": {
          "mean": 3.0625,
          "median": 3.0,
          "sd": 0.7474,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 11,
      "rank": 3,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 3,
      "configuration_id": "flux-3-full",
      "label": "FLUX 3 Full",
      "family": "Black Forest Labs FLUX 3",
      "factual_score": 5,
      "factual_score_max": 8,
      "event_success": {
        "success": 4,
        "not_success": 0,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 1,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 0,
        "not_success": 1,
        "no_consensus": 3,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 1,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "no_consensus",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3.1333,
          "median": 3,
          "sd": 0.8844,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "temporal_causal_coherence": {
          "mean": 3.0667,
          "median": 3,
          "sd": 0.6799,
          "numeric_responses": 15,
          "na_responses": 1
        },
        "physical_social_plausibility": {
          "mean": 3.125,
          "median": 3.0,
          "sd": 0.5995,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 7,
      "rank": 6,
      "tied_with": 0,
      "shared_rank": false
    },
    {
      "canonical_position": 6,
      "configuration_id": "veo-3.1-standard",
      "label": "Veo 3.1 Standard",
      "family": "Google Veo 3.1",
      "factual_score": 4,
      "factual_score_max": 8,
      "event_success": {
        "success": 3,
        "not_success": 0,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 0,
        "no_consensus": 3,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 0,
        "no_consensus": 3,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 0,
        "no_consensus": 3,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3.1875,
          "median": 3.5,
          "sd": 0.8817,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "temporal_causal_coherence": {
          "mean": 2.5625,
          "median": 2.0,
          "sd": 0.998,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "physical_social_plausibility": {
          "mean": 3.0625,
          "median": 3.0,
          "sd": 0.5555,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 6,
      "rank": 7,
      "tied_with": 0,
      "shared_rank": false
    },
    {
      "canonical_position": 7,
      "configuration_id": "happyhorse-1.1",
      "label": "HappyHorse 1.1",
      "family": "HappyHorse",
      "factual_score": 3,
      "factual_score_max": 8,
      "event_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 1.6,
          "median": 1.5,
          "sd": 0.6633,
          "numeric_responses": 10,
          "na_responses": 6
        },
        "temporal_causal_coherence": {
          "mean": 3.2727,
          "median": 3,
          "sd": 0.7497,
          "numeric_responses": 11,
          "na_responses": 5
        },
        "physical_social_plausibility": {
          "mean": 3.5,
          "median": 3.5,
          "sd": 0.5,
          "numeric_responses": 12,
          "na_responses": 4
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 9,
      "rank": 8,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 14,
      "configuration_id": "sora-2-pro",
      "label": "Sora 2 Pro",
      "family": "OpenAI Sora",
      "factual_score": 3,
      "factual_score_max": 8,
      "event_success": {
        "success": 2,
        "not_success": 1,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 3,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 3,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 3,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3.1,
          "median": 3.0,
          "sd": 0.8307,
          "numeric_responses": 10,
          "na_responses": 6
        },
        "temporal_causal_coherence": {
          "mean": 3.3,
          "median": 3.5,
          "sd": 0.781,
          "numeric_responses": 10,
          "na_responses": 6
        },
        "physical_social_plausibility": {
          "mean": 2.9167,
          "median": 3.0,
          "sd": 0.862,
          "numeric_responses": 12,
          "na_responses": 4
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 10,
      "rank": 8,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 8,
      "configuration_id": "kling-video-3.0-omni",
      "label": "Kling VIDEO 3.0 Omni",
      "family": "Kling 3",
      "factual_score": 2,
      "factual_score_max": 8,
      "event_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 3,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 3,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 3,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 3,
        "requested": 4
      },
      "refusals": {
        "count": 1,
        "scenes": [
          "FB-074"
        ],
        "marker": "R"
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "refused",
          "event": null,
          "strict": null,
          "full": null,
          "primary_causal": null,
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 3,
          "median": 3.0,
          "sd": 0.7071,
          "numeric_responses": 4,
          "na_responses": 8
        },
        "temporal_causal_coherence": {
          "mean": 3.5,
          "median": 3.5,
          "sd": 0.9574,
          "numeric_responses": 6,
          "na_responses": 6
        },
        "physical_social_plausibility": {
          "mean": 3.1111,
          "median": 3,
          "sd": 0.737,
          "numeric_responses": 9,
          "na_responses": 3
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 9,
      "human_questions_with_consensus": 9,
      "rank": 10,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 11,
      "configuration_id": "minimax-h3-2k-api",
      "label": "MiniMax H3 2K API",
      "family": "MiniMax H3",
      "factual_score": 2,
      "factual_score_max": 8,
      "event_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 2,
        "not_success": 2,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "success",
          "points": 0
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 2.4286,
          "median": 3,
          "sd": 1.2936,
          "numeric_responses": 7,
          "na_responses": 9
        },
        "temporal_causal_coherence": {
          "mean": 2.875,
          "median": 3.0,
          "sd": 1.0533,
          "numeric_responses": 8,
          "na_responses": 8
        },
        "physical_social_plausibility": {
          "mean": 3,
          "median": 3,
          "sd": 0.603,
          "numeric_responses": 11,
          "na_responses": 5
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 10,
      "rank": 10,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 13,
      "configuration_id": "sora-2",
      "label": "Sora 2",
      "family": "OpenAI Sora",
      "factual_score": 2,
      "factual_score_max": 8,
      "event_success": {
        "success": 1,
        "not_success": 1,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "success",
          "full": "success",
          "primary_causal": "success",
          "points": 2
        },
        "FB-074": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 2.2727,
          "median": 2,
          "sd": 1.1355,
          "numeric_responses": 11,
          "na_responses": 5
        },
        "temporal_causal_coherence": {
          "mean": 2.9091,
          "median": 3,
          "sd": 0.9,
          "numeric_responses": 11,
          "na_responses": 5
        },
        "physical_social_plausibility": {
          "mean": 2.8182,
          "median": 3,
          "sd": 0.8332,
          "numeric_responses": 11,
          "na_responses": 5
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 6,
      "rank": 10,
      "tied_with": 2,
      "shared_rank": true
    },
    {
      "canonical_position": 5,
      "configuration_id": "veo-3.1-fast",
      "label": "Veo 3.1 Fast",
      "family": "Google Veo 3.1",
      "factual_score": 1,
      "factual_score_max": 8,
      "event_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 0,
        "not_success": 3,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 0,
        "not_success": 1,
        "no_consensus": 3,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 1
        },
        "FB-074": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "not_success",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "no_consensus",
          "points": 0
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 2.3125,
          "median": 2.5,
          "sd": 1.044,
          "numeric_responses": 16,
          "na_responses": 0
        },
        "temporal_causal_coherence": {
          "mean": 1.7143,
          "median": 1.5,
          "sd": 0.7954,
          "numeric_responses": 14,
          "na_responses": 2
        },
        "physical_social_plausibility": {
          "mean": 2.375,
          "median": 3.0,
          "sd": 0.927,
          "numeric_responses": 16,
          "na_responses": 0
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 7,
      "rank": 13,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 9,
      "configuration_id": "ltx-2.5-fast",
      "label": "LTX-2.5 Fast",
      "family": "LTX-2.5",
      "factual_score": 1,
      "factual_score_max": 8,
      "event_success": {
        "success": 1,
        "not_success": 2,
        "no_consensus": 1,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 0,
        "not_success": 2,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 0,
        "not_success": 2,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 0,
        "not_success": 2,
        "no_consensus": 2,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "no_consensus",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "success",
          "strict": "no_consensus",
          "full": "no_consensus",
          "primary_causal": "no_consensus",
          "points": 1
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 1,
          "median": 1.0,
          "sd": 0.0,
          "numeric_responses": 6,
          "na_responses": 10
        },
        "temporal_causal_coherence": {
          "mean": 2.8333,
          "median": 3.0,
          "sd": 0.8975,
          "numeric_responses": 6,
          "na_responses": 10
        },
        "physical_social_plausibility": {
          "mean": 2.7,
          "median": 3.0,
          "sd": 0.6403,
          "numeric_responses": 10,
          "na_responses": 6
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 5,
      "rank": 13,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 10,
      "configuration_id": "ltx-2.5-pro",
      "label": "LTX-2.5 Pro",
      "family": "LTX-2.5",
      "factual_score": 0,
      "factual_score_max": 8,
      "event_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 1,
          "median": 1.0,
          "sd": 0.0,
          "numeric_responses": 2,
          "na_responses": 14
        },
        "temporal_causal_coherence": {
          "mean": 3.5,
          "median": 3.5,
          "sd": 0.5,
          "numeric_responses": 2,
          "na_responses": 14
        },
        "physical_social_plausibility": {
          "mean": 2.9091,
          "median": 3,
          "sd": 0.5143,
          "numeric_responses": 11,
          "na_responses": 5
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 11,
      "rank": 15,
      "tied_with": 1,
      "shared_rank": true
    },
    {
      "canonical_position": 16,
      "configuration_id": "grok-imagine-video-1.5",
      "label": "Grok Imagine Video 1.5",
      "family": "xAI Grok Imagine",
      "factual_score": 0,
      "factual_score_max": 8,
      "event_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "strict_scene_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "full_factual_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "primary_causal_success": {
        "success": 0,
        "not_success": 4,
        "no_consensus": 0,
        "evaluated": 4,
        "requested": 4
      },
      "refusals": {
        "count": 0,
        "scenes": [],
        "marker": null
      },
      "scenes": {
        "FB-C02": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-014": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-074": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        },
        "FB-512": {
          "status": "generated",
          "event": "not_success",
          "strict": "not_success",
          "full": "not_success",
          "primary_causal": "not_success",
          "points": 0
        }
      },
      "ratings": {
        "acoustic_plausibility": {
          "mean": 1,
          "median": 1,
          "sd": null,
          "numeric_responses": 1,
          "na_responses": 15
        },
        "temporal_causal_coherence": {
          "mean": 3,
          "median": 3,
          "sd": null,
          "numeric_responses": 1,
          "na_responses": 15
        },
        "physical_social_plausibility": {
          "mean": 3.4444,
          "median": 3,
          "sd": 0.4969,
          "numeric_responses": 9,
          "na_responses": 7
        }
      },
      "reviewers_per_clip": 4,
      "human_questions": 12,
      "human_questions_with_consensus": 11,
      "rank": 15,
      "tied_with": 1,
      "shared_rank": true
    }
  ]
}
