{ "rv2_supersede_e2e": { "cases": 200, "legacy_accuracy_pct": 73.0, "accuracy_pct": 80.0, "answerable_accuracy_pct": 84.0, "unknown_refusal_pct": 52.0, "wrong_abstention_pct": 4.0, "per_category": { "alias_paraphrase": { "cases": 25, "legacy_accuracy_pct": 100.0, "accuracy_pct": 100.0 }, "long_fact": { "cases": 25, "legacy_accuracy_pct": 76.0, "accuracy_pct": 76.0 }, "multi_entity": { "cases": 25, "legacy_accuracy_pct": 96.0, "accuracy_pct": 96.0 }, "multi_hop": { "cases": 25, "legacy_accuracy_pct": 44.0, "accuracy_pct": 100.0 }, "near_miss": { "cases": 25, "legacy_accuracy_pct": 100.0, "accuracy_pct": 100.0 }, "noise_context": { "cases": 25, "legacy_accuracy_pct": 72.0, "accuracy_pct": 72.0 }, "unknown_attribute": { "cases": 25, "legacy_accuracy_pct": 52.0, "accuracy_pct": 52.0 }, "update_conflict": { "cases": 25, "legacy_accuracy_pct": 44.0, "accuracy_pct": 44.0 } } }, "rv2_anslast_e2e": { "cases": 200, "legacy_accuracy_pct": 67.0, "accuracy_pct": 73.5, "answerable_accuracy_pct": 76.57, "unknown_refusal_pct": 52.0, "wrong_abstention_pct": 9.71, "per_category": { "alias_paraphrase": { "cases": 25, "legacy_accuracy_pct": 100.0, "accuracy_pct": 100.0 }, "long_fact": { "cases": 25, "legacy_accuracy_pct": 76.0, "accuracy_pct": 76.0 }, "multi_entity": { "cases": 25, "legacy_accuracy_pct": 96.0, "accuracy_pct": 96.0 }, "multi_hop": { "cases": 25, "legacy_accuracy_pct": 48.0, "accuracy_pct": 100.0 }, "near_miss": { "cases": 25, "legacy_accuracy_pct": 100.0, "accuracy_pct": 100.0 }, "noise_context": { "cases": 25, "legacy_accuracy_pct": 0.0, "accuracy_pct": 0.0 }, "unknown_attribute": { "cases": 25, "legacy_accuracy_pct": 52.0, "accuracy_pct": 52.0 }, "update_conflict": { "cases": 25, "legacy_accuracy_pct": 64.0, "accuracy_pct": 64.0 } } } }