{ "n_samples": 24, "tier2_accuracy": { "proof_status": 0.7083 }, "results": { "proof_status_centroid": { "tier2_accuracy": 0.7083, "tier2_top2": 1.0, "tier1_accuracy": null, "majority_baseline": 0.8333, "tier2_beats_tier1": true, "improves_over_baseline": -0.15, "n_samples": 24, "distribution": { "verified": 20, "failed": 4 } }, "proof_status_knn_3": { "tier2_accuracy": 0.7083, "tier2_top2": 1.0, "tier1_accuracy": null, "majority_baseline": 0.8333, "tier2_beats_tier1": true, "improves_over_baseline": -0.15, "n_samples": 24, "distribution": { "verified": 20, "failed": 4 } }, "proof_method_label_centroid": { "tier2_accuracy": 0.2083, "tier2_top2": 0.25, "tier1_accuracy": 0.0952, "majority_baseline": 0.2083, "tier2_beats_tier1": true, "improves_over_baseline": 0.0, "n_samples": 24, "distribution": { "apply": 2, "ring": 1, "cases": 2, "constructor": 1, "rfl": 2, "rewrite": 5, "omega": 5, "have": 1, "induction": 3, "simp": 1, "intro": 1 } }, "proof_method_label_knn_3": { "tier2_accuracy": 0.2083, "tier2_top2": 0.25, "tier1_accuracy": 0.0714, "majority_baseline": 0.2083, "tier2_beats_tier1": true, "improves_over_baseline": 0.0, "n_samples": 24, "distribution": { "apply": 2, "ring": 1, "cases": 2, "constructor": 1, "rfl": 2, "rewrite": 5, "omega": 5, "have": 1, "induction": 3, "simp": 1, "intro": 1 } }, "domain_label_centroid": { "tier2_accuracy": 0.625, "tier2_top2": 0.75, "tier1_accuracy": 0.1905, "majority_baseline": 0.3333, "tier2_beats_tier1": true, "improves_over_baseline": 0.875, "n_samples": 24, "distribution": { "logic": 7, "algebra": 2, "type_error": 2, "arithmetic": 8, "order": 3, "equality": 2 } }, "domain_label_knn_3": { "tier2_accuracy": 0.625, "tier2_top2": 0.75, "tier1_accuracy": 0.3095, "majority_baseline": 0.3333, "tier2_beats_tier1": true, "improves_over_baseline": 0.875, "n_samples": 24, "distribution": { "logic": 7, "algebra": 2, "type_error": 2, "arithmetic": 8, "order": 3, "equality": 2 } }, "manual_rrc_shape_centroid": { "tier2_accuracy": 0.6667, "tier2_top2": 0.9167, "tier1_accuracy": 0.381, "majority_baseline": 0.2917, "tier2_beats_tier1": true, "improves_over_baseline": 1.286, "n_samples": 24, "distribution": { "LogogramProjection": 7, "SignalShapedRouteCompiler": 4, "HoldForUnlawfulOrUnderspecifiedShape": 5, "ProjectableGeometryTopology": 3, "CognitiveLoadField": 1, "CadForceProbeReceipt": 4 } }, "manual_rrc_shape_knn_3": { "tier2_accuracy": 0.6667, "tier2_top2": 0.9167, "tier1_accuracy": 0.3333, "majority_baseline": 0.2917, "tier2_beats_tier1": true, "improves_over_baseline": 1.286, "n_samples": 24, "distribution": { "LogogramProjection": 7, "SignalShapedRouteCompiler": 4, "HoldForUnlawfulOrUnderspecifiedShape": 5, "ProjectableGeometryTopology": 3, "CognitiveLoadField": 1, "CadForceProbeReceipt": 4 } } }, "conclusion": { "tier2_wins": 8, "total_comparable": 6 } }