Upload _reasoning_rl_multiseed/eval_reasoning_t3_v7r128_postRL_alpha1_s2_par_20260506_221253/score.json with huggingface_hub

_reasoning_rl_multiseed/eval_reasoning_t3_v7r128_postRL_alpha1_s2_par_20260506_221253/score.json

@@ -0,0 +1,71 @@
+{
+  "n_rows": 50,
+  "format": {
+    "reasoning_tags_rate": 0.64,
+    "dna_tags_rate": 0.0,
+    "cell_mention_rate": 0.78,
+    "mean_len_chars": 907.2,
+    "p10_len_chars": 562.9,
+    "p90_len_chars": 1381.2
+  },
+  "tf_grounding": {
+    "mean_tf_grounded_rate": 0.23970945554855788,
+    "mean_n_cited": 14.38,
+    "mean_n_grounded": 6.46,
+    "mean_n_canonical_only": 0.4,
+    "mean_n_hallucinated": 7.52,
+    "mean_motif_consensus": 0.3864917449198997,
+    "mean_prog_coverage": 0.11304761904761905
+  },
+  "per_cell": {
+    "Ast": {
+      "n": 5,
+      "tf_grounded_rate": 0.1985060690943044,
+      "n_cited": 12.0,
+      "len_chars": 788.8,
+      "cell_mention": 1.0
+    },
+    "End": {
+      "n": 3,
+      "tf_grounded_rate": 0.3333333333333333,
+      "n_cited": 5.333333333333333,
+      "len_chars": 1102.0,
+      "cell_mention": 0.0
+    },
+    "Ex": {
+      "n": 15,
+      "tf_grounded_rate": 0.3663495465453103,
+      "n_cited": 23.266666666666666,
+      "len_chars": 1031.6666666666667,
+      "cell_mention": 0.8
+    },
+    "In": {
+      "n": 4,
+      "tf_grounded_rate": 0.05625,
+      "n_cited": 8.25,
+      "len_chars": 997.5,
+      "cell_mention": 1.0
+    },
+    "Mic": {
+      "n": 13,
+      "tf_grounded_rate": 0.1733364093533585,
+      "n_cited": 11.384615384615385,
+      "len_chars": 827.6153846153846,
+      "cell_mention": 0.7692307692307693
+    },
+    "OPC": {
+      "n": 2,
+      "tf_grounded_rate": 0.16666666666666666,
+      "n_cited": 7.5,
+      "len_chars": 972.0,
+      "cell_mention": 0.5
+    },
+    "Oli": {
+      "n": 8,
+      "tf_grounded_rate": 0.21074907235621523,
+      "n_cited": 12.25,
+      "len_chars": 742.75,
+      "cell_mention": 0.875
+    }
+  }
+}