verteryx—

the ledger

every number we have ever published, in one place. nothing curated. nothing deleted. corrections never overwrite — they append.

01 14 d ago finding the law · anthropic_claude-fable-5-growth30-citefix + citation library 98% found 115 of 118 grounds a specialist would raise. misused legal authority in 27 of 30 cases.
02 14 d ago finding the law · anthropic_claude-fable-5-growth30-citefix + citation library 98% found 116 of 118 grounds a specialist would raise. misused legal authority in 16 of 30 cases.
03 14 d ago finding the law · deepseek_deepseek-v4-pro-growth30-growth30-traps2 + citation library 91% found 107 of 118 grounds a specialist would raise. misused legal authority in 12 of 30 cases.
04 14 d ago finding the law · deepseek_deepseek-v4-pro-growth30-growth30-mid + citation library 88% found 104 of 118 grounds a specialist would raise. misused legal authority in 10 of 30 cases.
05 23 d ago finding the law · sonder (8B, local) + citation library + revise loop 71% found 84 of 118 grounds a specialist would raise. misused legal authority in 25 of 30 cases.
06 23 d ago finding the law · sonder (8B, local) + citation library 71% found 84 of 118 grounds a specialist would raise. misused legal authority in 30 of 30 cases.
07 23 d ago finding the law · sonder-qwen3-8b-growth30 + citation library 70% found 82 of 118 grounds a specialist would raise. misused legal authority in 30 of 30 cases.
08 50 d ago finding the law · anthropic_claude-fable-5-growth30-mech + citation library 98% found 115 of 118 grounds a specialist would raise. misused legal authority in 6 of 30 cases.
09 50 d ago finding the law · anthropic_claude-fable-5-growth30-growth30 + citation library 78% found 28 of 36 grounds a specialist would raise. misused legal authority in 7 of 9 cases.
10 51 d ago finding the law · anthropic_claude-fable-5-denial-cases-v0-teacher-v7 + citation library 100% found 151 of 151 grounds a specialist would raise. misused legal authority in 24 of 50 cases.
11 51 d ago finding the law · anthropic_claude-fable-5-denial-cases-v0-teacher-v7 + citation library 98% found 148 of 151 grounds a specialist would raise. misused legal authority in 19 of 50 cases.
12 52 d ago finding the law · sonder (8B, local) + citation library 80% found 120 of 151 grounds a specialist would raise. misused legal authority in 47 of 50 cases.
13 52 d ago finding the law · mlx_mlx-community_Qwen3-8B-4bit-sample10-iter55-s10 + citation library 70% found 21 of 30 grounds a specialist would raise. misused legal authority in 9 of 10 cases.
14 52 d ago finding the law · mlx_mlx-community_Qwen3-8B-4bit-held_out_cases-ft-holdout + citation library 71% found 105 of 148 grounds a specialist would raise. misused legal authority in 43 of 49 cases.
15 52 d ago finding the law · mlx_mlx-community_Qwen3-8B-4bit-ft + citation library 70% found 105 of 151 grounds a specialist would raise. misused legal authority in 46 of 50 cases.
16 52 d ago finding the law · anthropic_claude-fable-5-eval100v5 + citation library 100% found 151 of 151 grounds a specialist would raise. misused legal authority in 18 of 50 cases.
17 52 d ago finding the law · anthropic_claude-fable-5-eval100v4 + citation library 99% found 149 of 151 grounds a specialist would raise. misused legal authority in 24 of 50 cases.
18 52 d ago finding the law · anthropic_claude-fable-5-eval100v3 + citation library 99% found 149 of 151 grounds a specialist would raise. misused legal authority in 25 of 50 cases.
19 52 d ago finding the law · sonder-qwen3-8b-prompts + citation library 76% found 114 of 151 grounds a specialist would raise. misused legal authority in 44 of 50 cases.
20 52 d ago finding the law · anthropic_claude-fable-5-eval100v2 + citation library 99% found 149 of 151 grounds a specialist would raise. misused legal authority in 19 of 50 cases.
21 52 d ago finding the law · anthropic_claude-fable-5-eval100 + citation library 98% found 148 of 151 grounds a specialist would raise. misused legal authority in 13 of 50 cases.
22 52 d ago finding the law · sonder (8B, local) + citation library + revise loop 82% found 124 of 151 grounds a specialist would raise. misused legal authority in 31 of 50 cases.
23 52 d ago finding the law · sonder (30B, local) + citation library 74% found 111 of 151 grounds a specialist would raise. misused legal authority in 40 of 50 cases.
24 52 d ago finding the law · sonder (30B, local) + citation library 72% found 109 of 151 grounds a specialist would raise. misused legal authority in 26 of 50 cases.
25 53 d ago finding the law · sonder (30B, local) + citation library + revise loop 72% found 108 of 151 grounds a specialist would raise. misused legal authority in 35 of 50 cases.
26 53 d ago finding the law · claude fable + citation library 98% found 148 of 151 grounds a specialist would raise. misused legal authority in 17 of 50 cases.
27 53 d ago finding the law · sonder (30B, local) + citation library + revise loop 64% found 97 of 151 grounds a specialist would raise. misused legal authority in 36 of 50 cases.
28 53 d ago finding the law · kimi k2 (1T, API) + citation library + revise loop 70% found 106 of 151 grounds a specialist would raise. misused legal authority in 14 of 50 cases.
29 53 d ago finding the law · claude fable + citation library + revise loop 90% found 136 of 151 grounds a specialist would raise. misused legal authority in 11 of 50 cases.
30 53 d ago finding the law · gpt-5.5 + citation library + revise loop 87% found 131 of 151 grounds a specialist would raise. misused legal authority in 8 of 50 cases.
31 53 d ago finding the law · kimi k2 (1T, API) + citation library 66% found 99 of 151 grounds a specialist would raise. misused legal authority in 27 of 50 cases.
32 53 d ago finding the law · gpt-5.5 + citation library 72% found 108 of 151 grounds a specialist would raise. misused legal authority in 4 of 50 cases.
33 53 d ago finding the law · gpt-5.6 + citation library 90% found 136 of 151 grounds a specialist would raise. misused legal authority in 2 of 50 cases.
34 53 d ago finding the law · kimi k2.7 (API) 69% found 104 of 151 grounds a specialist would raise. misused legal authority in 37 of 50 cases.
35 54 d ago reading denials · sonder (30B, local) 94% given 50 denial letters, the model named the real reason for denial in 47. on the letters written to disguise it, 80%.
36 54 d ago reading denials · sonder (8B, local) 96% given 50 denial letters, the model named the real reason for denial in 48. on the letters written to disguise it, 80%.
37 54 d ago reading denials · kimi k2.7 (API) 94% given 50 denial letters, the model named the real reason for denial in 47. on the letters written to disguise it, 80%.
38 103 d ago finding the law · deepseek_deepseek-v4-pro 87% found 131 of 151 grounds a specialist would raise. misused legal authority in 11 of 50 cases.
39 103 d ago finding the law · sonder (8B, local) 76% found 114 of 151 grounds a specialist would raise. misused legal authority in 35 of 50 cases.
40 103 d ago finding the law · claude fable 16% found 24 of 151 grounds a specialist would raise. misused legal authority in 0 of 50 cases.
41 103 d ago finding the law · gpt-5.5 93% found 141 of 151 grounds a specialist would raise. misused legal authority in 2 of 50 cases.
42 103 d ago finding the law · sonder (8B, local) + citation library + operational-grounds prompt 70% found 106 of 151 grounds a specialist would raise. misused legal authority in 28 of 50 cases.
43 104 d ago finding the law · gpt-5.5 + citation library + operational-grounds prompt 91% found 137 of 151 grounds a specialist would raise. misused legal authority in 1 of 50 cases.
44 104 d ago drafting appeals · sonder (8B, local) 254 flagged the verifier read 50 complete appeal letters and flagged 254 unsupported claims. it does not catch a real provision cited for a proposition it does not hold.
45 104 d ago drafting appeals · kimi k2 (1T, API) 281 flagged the verifier read 50 complete appeal letters and flagged 281 unsupported claims. it does not catch a real provision cited for a proposition it does not hold.
46 105 d ago finding the law · sonder (8B, local) 63% found 95 of 151 grounds a specialist would raise. misused legal authority in 44 of 50 cases.
47 105 d ago finding the law · kimi k2 (1T, API) 74% found 112 of 151 grounds a specialist would raise. misused legal authority in 47 of 50 cases.
48 105 d ago reading denials · kimi k2 (1T, API) 98% given 50 denial letters, the model named the real reason for denial in 49. on the letters written to disguise it, 90%.

every entry above ran on real denial letters. the raw transcripts stay private — but the numbers, the models, the dates, and the methods are yours to check.