Root Cause Analysis on RE2SS Sock Shop with multimodal data (test) benchmark leaderboard · SOTA2 Research

Root Cause Analysis on RE2SS Sock Shop with multimodal data (test)

87CPU Top-1 AccuracyPRISM

Evaluation Results

Method	Links
PRISM2026.01		87	100	97	73	93	89	93	93	93	80	100	96	100	100	100	80	87	91	86	96	94	—
Simple-Traversal2026.01		27	40	37	7	47	40	7	60	44	0	40	25	20	40	35	20	33	31	13	43	35	—
Smooth-Traversal2026.01		20	27	24	0	13	8	0	27	21	0	20	12	13	27	21	13	27	28	8	23	19	—
PC-PageRank2026.01		20	33	29	7	33	27	13	20	20	13	27	21	13	27	24	33	40	41	17	30	27	—
Score-Ordering2026.01		20	40	41	7	40	37	13	47	43	13	53	45	13	40	36	13	53	49	13	46	42	—
Counterfactual2026.01		13	13	13	0	7	4	13	27	24	27	27	29	7	7	7	7	7	12	11	14	15	—
Cholesky2026.01		7	27	27	7	13	20	20	53	40	7	40	35	0	7	16	7	40	33	8	30	28	—
BARO2026.01		0	73	60	0	67	57	67	93	85	7	93	71	13	100	79	0	60	51	14	81	67	—