diff --git a/PAPER.md b/PAPER.md index faa340f..182fe9b 100644 --- a/PAPER.md +++ b/PAPER.md @@ -31,7 +31,8 @@ A complete attribution program then deflates the mechanism's mystique: the loop's content is *amortizable* (plan-distillation into the same adapter, recurrence-free, matches it; nothing stacks; looping distilled weights degrades them), width rivals depth (trained pause registers reach 36.4%), -and compute-matched token baselines win overall accuracy outright. What +and verifier-assisted (oracle) sampling wins overall accuracy at matched +compute — though the *deployable* selector loses that edge entirely. What survives is precise: the implant owns exactly the plan-dependent slice at zero visible tokens and zero decode cost, transfers with the substrate rather than the task, and its placement is dictated by the lens. At 12B a @@ -88,11 +89,14 @@ not laws.)* (parallel, prefill-shaped), zero decode overhead, bit-exact KV-cache write-in, k=0 recovers the base model exactly. Its competition at comparable compute (accounting in Appendix A — FLOPs, wall-clock, and - token budget do not rank the arms the same way): best-of-3 sampling wins - overall accuracy outright (57.2%); a - 50-token visible plan ties the hard bucket. The value proposition is - *only*: no visible tokens, no decode latency, and the hard-slice - specialization (distill's 46% > budget-CoT's 40% > best-of-3's 33%). + token budget do not rank the arms the same way): *oracle* best-of-3 + (verifier-assisted) wins overall accuracy (57.8%, paired p=0.020 vs + loop), but the *deployable* logprob-selected variant drops to 55.0% + overall / 27.3% hard — indistinguishable from the latent arms overall + and directionally behind on hard. A 50-token visible plan ties the hard + bucket. The value proposition without a verifier: no visible tokens, no + decode latency, and the hard-slice specialization (distill's 46% > + budget-CoT's 40% > deployable sampling's 27%). 6. **Scale transfers only with a state-dependent stability dial.** At 12B the 2B-tuned constant α=0.3 collapses overall accuracy (72.6%→43.0%); the @@ -228,20 +232,26 @@ distinctive value is that it finds this content *without* plan supervision ### 3.4 Compute-matched honesty At approximately matched FLOPs (Appendix A gives the accounting, separated -into FLOPs, wall-clock, and token budget), token-space baselines are strong: -best-of-3 sampling wins overall accuracy against every latent arm (57.2%, -CI [52.8, 61.5], vs loop 53.6 [49.2, 57.9] — point estimate higher, CIs -overlap) by preserving easy items perfectly while sampling rescues some hard -ones. A 50-token visible plan ties the loop's hard bucket. Both baselines -are being rerun with per-item logs to enable paired tests against the latent -arms; until those land, the overall-accuracy comparison rests on overlapping -CIs and is stated as point-estimate-level. [BASELINES-PI PENDING] -The latent implant's surviving advantages are qualitative: zero visible -tokens (silent), zero decode overhead (prefill-parallel; sampling and CoT -pay serially at bandwidth-bound decode), and the hard-slice crown under -distillation (46% vs 40% budget-CoT vs 33% best-of-3). For deployment this -means: the implant is a *latency/token-budget* technology with a side -specialization in plan-dependent items — not an accuracy technology. +into FLOPs, wall-clock, and token budget), the token-space comparison +splits into two very different claims: + +| best-of-3 variant | overall | hard | vs loop (paired) | +|---|---|---|---| +| **oracle** (any-of-3 passes; needs a perfect verifier) | 57.8% | 34.5% | beats loop overall, p=0.020 | +| **deployable** (highest mean logprob of 3) | 55.0% | 27.3% | n.s. overall (p=0.47); loop ahead on hard 16–7 (p=0.09) | + +The earlier draft's "sampling wins overall" was the **oracle** number — an +upper bound requiring an external verifier that MBPP's own tests provide +but a deployment does not. With the deployable selector (identical seeded +samples, so the comparison is exact), best-of-3 is statistically +indistinguishable from the latent arms overall, *behind* them +directionally on the hard bucket, and pays ≈3× visible tokens and serial +decode for it. Budget-CoT-50 remains the strongest honest token baseline +(53.8% overall, hard 40.0%). The implant's advantages at matched compute +without a verifier: zero visible tokens, zero decode overhead, and the +hard-slice crown under distillation (46%). Where a task *does* come with a +cheap verifier, oracle-style sampling is the better overall-accuracy +spend — both halves belong in the deployment picture. ### 3.5 Width vs depth, and the task boundary diff --git a/results-loop/STATS.md b/results-loop/STATS.md index c926b59..e991d6d 100644 --- a/results-loop/STATS.md +++ b/results-loop/STATS.md @@ -31,6 +31,21 @@ - Rust loop k=4 vs k=0, overall: A-only 11, B-only 5, n=154, p=0.2101 (n.s.) - Rust loop k=4 vs k=0, hard: A-only 0, B-only 4, n=25, p=0.125 (n.s.) +## Token baselines (paired, per-item) + +- **best-of-3 ORACLE (any-pass)**: overall 0.578 [0.534, 0.621] (n=500); hard 0.345 [0.234, 0.477] (n=55) +- **best-of-3 oracle (selector run)**: overall 0.578 [0.534, 0.621] (n=500); hard 0.345 [0.234, 0.477] (n=55) +- **best-of-3 DEPLOYABLE (logprob-selected)**: overall 0.550 [0.506, 0.593] (n=500); hard 0.273 [0.173, 0.402] (n=55) +- bo3-oracle vs loop k=4, overall: arm-only 27, bo3-only 48, p=0.0203 (**significant**) +- bo3-oracle vs loop k=4, hard: arm-only 14, bo3-only 9, p=0.4049 (n.s.) +- bo3-oracle vs distill k=1, overall: arm-only 27, bo3-only 44, p=0.05681 (n.s.) +- bo3-oracle vs distill k=1, hard: arm-only 14, bo3-only 10, p=0.5413 (n.s.) +- bo3-deployable vs loop k=4, overall: arm-only 31, bo3-only 38, p=0.4704 (n.s.) +- bo3-deployable vs loop k=4, hard: arm-only 16, bo3-only 7, p=0.09314 (n.s.) +- bo3-deployable vs distill k=1, overall: arm-only 31, bo3-only 34, p=0.8043 (n.s.) +- bo3-deployable vs distill k=1, hard: arm-only 15, bo3-only 7, p=0.1338 (n.s.) +(token-baseline per-item files incomplete: [Errno 2] No such file or directory: '/home/nils/jspace/results-loop/eval_budgetcot_pi.json') + ## Pooled hard bucket (MBPP + HumanEval + Rust) Paired within-item k>0 vs k=0, counts pooled across benchmarks (loop arm; distill pooled where available). diff --git a/results-loop/eval_bestof3_pi.json b/results-loop/eval_bestof3_pi.json new file mode 100644 index 0000000..ef646de --- /dev/null +++ b/results-loop/eval_bestof3_pi.json @@ -0,0 +1,2010 @@ +{ + "acc": 0.578, + "by_label": { + "easy": 0.9884615384615385, + "hard": 0.34545454545454546, + "drop": 0.07027027027027027 + }, + "per_item": [ + { + "task_id": 11, + "ok": true + }, + { + "task_id": 12, + "ok": true + }, + { + "task_id": 13, + "ok": false + }, + { + "task_id": 14, + "ok": true + }, + { + "task_id": 15, + "ok": false + }, + { + "task_id": 16, + "ok": false + }, + { + "task_id": 17, + "ok": true + }, + { + "task_id": 18, + "ok": true + }, + { + "task_id": 19, + "ok": true + }, + { + "task_id": 20, + "ok": false + }, + { + "task_id": 21, + "ok": false + }, + { + "task_id": 22, + "ok": true + }, + { + "task_id": 23, + "ok": true + }, + { + "task_id": 24, + "ok": false + }, + { + "task_id": 25, + "ok": true + }, + { + "task_id": 26, + "ok": false + }, + { + "task_id": 27, + "ok": true + }, + { + "task_id": 28, + "ok": true + }, + { + "task_id": 29, + "ok": true + }, + { + "task_id": 30, + "ok": true + }, + { + "task_id": 31, + "ok": false + }, + { + "task_id": 32, + "ok": true + }, + { + "task_id": 33, + "ok": false + }, + { + "task_id": 34, + "ok": false + }, + { + "task_id": 35, + "ok": false + }, + { + "task_id": 36, + "ok": false + }, + { + "task_id": 37, + "ok": true + }, + { + "task_id": 38, + "ok": false + }, + { + "task_id": 39, + "ok": false + }, + { + "task_id": 40, + "ok": true + }, + { + "task_id": 41, + "ok": true + }, + { + "task_id": 42, + "ok": false + }, + { + "task_id": 43, + "ok": false + }, + { + "task_id": 44, + "ok": true + }, + { + "task_id": 45, + "ok": true + }, + { + "task_id": 46, + "ok": true + }, + { + "task_id": 47, + "ok": false + }, + { + "task_id": 48, + "ok": false + }, + { + "task_id": 49, + "ok": true + }, + { + "task_id": 50, + "ok": true + }, + { + "task_id": 51, + "ok": true + }, + { + "task_id": 52, + "ok": true + }, + { + "task_id": 53, + "ok": true + }, + { + "task_id": 54, + "ok": true + }, + { + "task_id": 55, + "ok": true + }, + { + "task_id": 56, + "ok": true + }, + { + "task_id": 57, + "ok": true + }, + { + "task_id": 58, + "ok": true + }, + { + "task_id": 59, + "ok": false + }, + { + "task_id": 60, + "ok": false + }, + { + "task_id": 61, + "ok": true + }, + { + "task_id": 62, + "ok": true + }, + { + "task_id": 63, + "ok": true + }, + { + "task_id": 64, + "ok": true + }, + { + "task_id": 65, + "ok": true + }, + { + "task_id": 66, + "ok": true + }, + { + "task_id": 67, + "ok": false + }, + { + "task_id": 68, + "ok": true + }, + { + "task_id": 69, + "ok": true + }, + { + "task_id": 70, + "ok": true + }, + { + "task_id": 71, + "ok": false + }, + { + "task_id": 72, + "ok": true + }, + { + "task_id": 73, + "ok": true + }, + { + "task_id": 74, + "ok": false + }, + { + "task_id": 75, + "ok": true + }, + { + "task_id": 76, + "ok": true + }, + { + "task_id": 77, + "ok": false + }, + { + "task_id": 78, + "ok": true + }, + { + "task_id": 79, + "ok": true + }, + { + "task_id": 80, + "ok": true + }, + { + "task_id": 81, + "ok": false + }, + { + "task_id": 82, + "ok": true + }, + { + "task_id": 83, + "ok": false + }, + { + "task_id": 84, + "ok": false + }, + { + "task_id": 85, + "ok": true + }, + { + "task_id": 86, + "ok": true + }, + { + "task_id": 87, + "ok": false + }, + { + "task_id": 88, + "ok": true + }, + { + "task_id": 89, + "ok": true + }, + { + "task_id": 90, + "ok": true + }, + { + "task_id": 91, + "ok": true + }, + { + "task_id": 92, + "ok": false + }, + { + "task_id": 93, + "ok": true + }, + { + "task_id": 94, + "ok": true + }, + { + "task_id": 95, + "ok": false + }, + { + "task_id": 96, + "ok": true + }, + { + "task_id": 97, + "ok": true + }, + { + "task_id": 98, + "ok": true + }, + { + "task_id": 99, + "ok": true + }, + { + "task_id": 100, + "ok": false + }, + { + "task_id": 101, + "ok": false + }, + { + "task_id": 102, + "ok": true + }, + { + "task_id": 103, + "ok": false + }, + { + "task_id": 104, + "ok": true + }, + { + "task_id": 105, + "ok": true + }, + { + "task_id": 106, + "ok": false + }, + { + "task_id": 107, + "ok": false + }, + { + "task_id": 108, + "ok": false + }, + { + "task_id": 109, + "ok": true + }, + { + "task_id": 110, + "ok": false + }, + { + "task_id": 111, + "ok": true + }, + { + "task_id": 112, + "ok": true + }, + { + "task_id": 113, + "ok": true + }, + { + "task_id": 114, + "ok": false + }, + { + "task_id": 115, + "ok": true + }, + { + "task_id": 116, + "ok": true + }, + { + "task_id": 117, + "ok": true + }, + { + "task_id": 118, + "ok": false + }, + { + "task_id": 119, + "ok": false + }, + { + "task_id": 120, + "ok": false + }, + { + "task_id": 121, + "ok": false + }, + { + "task_id": 122, + "ok": false + }, + { + "task_id": 123, + "ok": false + }, + { + "task_id": 124, + "ok": false + }, + { + "task_id": 125, + "ok": false + }, + { + "task_id": 126, + "ok": false + }, + { + "task_id": 127, + "ok": true + }, + { + "task_id": 128, + "ok": true + }, + { + "task_id": 129, + "ok": false + }, + { + "task_id": 130, + "ok": true + }, + { + "task_id": 131, + "ok": true + }, + { + "task_id": 132, + "ok": true + }, + { + "task_id": 133, + "ok": true + }, + { + "task_id": 134, + "ok": false + }, + { + "task_id": 135, + "ok": true + }, + { + "task_id": 136, + "ok": false + }, + { + "task_id": 137, + "ok": false + }, + { + "task_id": 138, + "ok": false + }, + { + "task_id": 139, + "ok": false + }, + { + "task_id": 140, + "ok": false + }, + { + "task_id": 141, + "ok": false + }, + { + "task_id": 142, + "ok": false + }, + { + "task_id": 143, + "ok": false + }, + { + "task_id": 144, + "ok": true + }, + { + "task_id": 145, + "ok": true + }, + { + "task_id": 146, + "ok": false + }, + { + "task_id": 147, + "ok": false + }, + { + "task_id": 148, + "ok": false + }, + { + "task_id": 149, + "ok": false + }, + { + "task_id": 150, + "ok": false + }, + { + "task_id": 151, + "ok": true + }, + { + "task_id": 152, + "ok": false + }, + { + "task_id": 153, + "ok": true + }, + { + "task_id": 154, + "ok": true + }, + { + "task_id": 155, + "ok": false + }, + { + "task_id": 156, + "ok": true + }, + { + "task_id": 157, + "ok": true + }, + { + "task_id": 158, + "ok": false + }, + { + "task_id": 159, + "ok": false + }, + { + "task_id": 160, + "ok": false + }, + { + "task_id": 161, + "ok": true + }, + { + "task_id": 162, + "ok": true + }, + { + "task_id": 163, + "ok": true + }, + { + "task_id": 164, + "ok": false + }, + { + "task_id": 165, + "ok": true + }, + { + "task_id": 166, + "ok": false + }, + { + "task_id": 167, + "ok": true + }, + { + "task_id": 168, + "ok": true + }, + { + "task_id": 169, + "ok": true + }, + { + "task_id": 170, + "ok": false + }, + { + "task_id": 171, + "ok": true + }, + { + "task_id": 172, + "ok": true + }, + { + "task_id": 173, + "ok": true + }, + { + "task_id": 174, + "ok": true + }, + { + "task_id": 175, + "ok": true + }, + { + "task_id": 176, + "ok": true + }, + { + "task_id": 177, + "ok": false + }, + { + "task_id": 178, + "ok": true + }, + { + "task_id": 179, + "ok": true + }, + { + "task_id": 180, + "ok": false + }, + { + "task_id": 181, + "ok": false + }, + { + "task_id": 182, + "ok": false + }, + { + "task_id": 183, + "ok": false + }, + { + "task_id": 184, + "ok": false + }, + { + "task_id": 185, + "ok": false + }, + { + "task_id": 186, + "ok": true + }, + { + "task_id": 187, + "ok": false + }, + { + "task_id": 188, + "ok": false + }, + { + "task_id": 189, + "ok": false + }, + { + "task_id": 190, + "ok": false + }, + { + "task_id": 191, + "ok": true + }, + { + "task_id": 192, + "ok": true + }, + { + "task_id": 193, + "ok": true + }, + { + "task_id": 194, + "ok": true + }, + { + "task_id": 195, + "ok": true + }, + { + "task_id": 196, + "ok": true + }, + { + "task_id": 197, + "ok": true + }, + { + "task_id": 198, + "ok": false + }, + { + "task_id": 199, + "ok": true + }, + { + "task_id": 200, + "ok": true + }, + { + "task_id": 201, + "ok": true + }, + { + "task_id": 202, + "ok": true + }, + { + "task_id": 203, + "ok": true + }, + { + "task_id": 204, + "ok": true + }, + { + "task_id": 205, + "ok": false + }, + { + "task_id": 206, + "ok": false + }, + { + "task_id": 207, + "ok": false + }, + { + "task_id": 208, + "ok": false + }, + { + "task_id": 209, + "ok": false + }, + { + "task_id": 210, + "ok": true + }, + { + "task_id": 211, + "ok": false + }, + { + "task_id": 212, + "ok": true + }, + { + "task_id": 213, + "ok": true + }, + { + "task_id": 214, + "ok": true + }, + { + "task_id": 215, + "ok": true + }, + { + "task_id": 216, + "ok": false + }, + { + "task_id": 217, + "ok": true + }, + { + "task_id": 218, + "ok": false + }, + { + "task_id": 219, + "ok": false + }, + { + "task_id": 220, + "ok": false + }, + { + "task_id": 221, + "ok": true + }, + { + "task_id": 222, + "ok": true + }, + { + "task_id": 223, + "ok": true + }, + { + "task_id": 224, + "ok": true + }, + { + "task_id": 225, + "ok": false + }, + { + "task_id": 226, + "ok": true + }, + { + "task_id": 227, + "ok": true + }, + { + "task_id": 228, + "ok": false + }, + { + "task_id": 229, + "ok": false + }, + { + "task_id": 230, + "ok": true + }, + { + "task_id": 231, + "ok": false + }, + { + "task_id": 232, + "ok": true + }, + { + "task_id": 233, + "ok": false + }, + { + "task_id": 234, + "ok": true + }, + { + "task_id": 235, + "ok": false + }, + { + "task_id": 236, + "ok": false + }, + { + "task_id": 237, + "ok": false + }, + { + "task_id": 238, + "ok": true + }, + { + "task_id": 239, + "ok": false + }, + { + "task_id": 240, + "ok": true + }, + { + "task_id": 241, + "ok": false + }, + { + "task_id": 242, + "ok": true + }, + { + "task_id": 243, + "ok": false + }, + { + "task_id": 244, + "ok": false + }, + { + "task_id": 245, + "ok": false + }, + { + "task_id": 246, + "ok": true + }, + { + "task_id": 247, + "ok": true + }, + { + "task_id": 248, + "ok": false + }, + { + "task_id": 249, + "ok": true + }, + { + "task_id": 250, + "ok": true + }, + { + "task_id": 251, + "ok": true + }, + { + "task_id": 252, + "ok": true + }, + { + "task_id": 253, + "ok": true + }, + { + "task_id": 254, + "ok": true + }, + { + "task_id": 255, + "ok": true + }, + { + "task_id": 256, + "ok": false + }, + { + "task_id": 257, + "ok": true + }, + { + "task_id": 258, + "ok": true + }, + { + "task_id": 259, + "ok": false + }, + { + "task_id": 260, + "ok": false + }, + { + "task_id": 261, + "ok": true + }, + { + "task_id": 262, + "ok": true + }, + { + "task_id": 263, + "ok": true + }, + { + "task_id": 264, + "ok": false + }, + { + "task_id": 265, + "ok": true + }, + { + "task_id": 266, + "ok": true + }, + { + "task_id": 267, + "ok": true + }, + { + "task_id": 268, + "ok": false + }, + { + "task_id": 269, + "ok": true + }, + { + "task_id": 270, + "ok": true + }, + { + "task_id": 271, + "ok": true + }, + { + "task_id": 272, + "ok": true + }, + { + "task_id": 273, + "ok": true + }, + { + "task_id": 274, + "ok": false + }, + { + "task_id": 275, + "ok": false + }, + { + "task_id": 276, + "ok": false + }, + { + "task_id": 277, + "ok": false + }, + { + "task_id": 278, + "ok": true + }, + { + "task_id": 279, + "ok": false + }, + { + "task_id": 280, + "ok": true + }, + { + "task_id": 281, + "ok": true + }, + { + "task_id": 282, + "ok": true + }, + { + "task_id": 283, + "ok": true + }, + { + "task_id": 284, + "ok": true + }, + { + "task_id": 285, + "ok": true + }, + { + "task_id": 286, + "ok": false + }, + { + "task_id": 287, + "ok": true + }, + { + "task_id": 288, + "ok": false + }, + { + "task_id": 289, + "ok": false + }, + { + "task_id": 290, + "ok": true + }, + { + "task_id": 291, + "ok": false + }, + { + "task_id": 292, + "ok": true + }, + { + "task_id": 293, + "ok": true + }, + { + "task_id": 294, + "ok": true + }, + { + "task_id": 295, + "ok": false + }, + { + "task_id": 296, + "ok": true + }, + { + "task_id": 297, + "ok": true + }, + { + "task_id": 298, + "ok": false + }, + { + "task_id": 299, + "ok": true + }, + { + "task_id": 300, + "ok": false + }, + { + "task_id": 301, + "ok": true + }, + { + "task_id": 302, + "ok": true + }, + { + "task_id": 303, + "ok": false + }, + { + "task_id": 304, + "ok": false + }, + { + "task_id": 305, + "ok": false + }, + { + "task_id": 306, + "ok": false + }, + { + "task_id": 307, + "ok": false + }, + { + "task_id": 308, + "ok": true + }, + { + "task_id": 309, + "ok": true + }, + { + "task_id": 310, + "ok": false + }, + { + "task_id": 311, + "ok": false + }, + { + "task_id": 312, + "ok": false + }, + { + "task_id": 313, + "ok": false + }, + { + "task_id": 314, + "ok": false + }, + { + "task_id": 315, + "ok": true + }, + { + "task_id": 316, + "ok": true + }, + { + "task_id": 317, + "ok": true + }, + { + "task_id": 318, + "ok": false + }, + { + "task_id": 319, + "ok": true + }, + { + "task_id": 320, + "ok": false + }, + { + "task_id": 321, + "ok": false + }, + { + "task_id": 322, + "ok": true + }, + { + "task_id": 323, + "ok": false + }, + { + "task_id": 324, + "ok": false + }, + { + "task_id": 325, + "ok": false + }, + { + "task_id": 326, + "ok": false + }, + { + "task_id": 327, + "ok": true + }, + { + "task_id": 328, + "ok": false + }, + { + "task_id": 329, + "ok": true + }, + { + "task_id": 330, + "ok": true + }, + { + "task_id": 331, + "ok": false + }, + { + "task_id": 332, + "ok": true + }, + { + "task_id": 333, + "ok": true + }, + { + "task_id": 334, + "ok": true + }, + { + "task_id": 335, + "ok": false + }, + { + "task_id": 336, + "ok": true + }, + { + "task_id": 337, + "ok": false + }, + { + "task_id": 338, + "ok": false + }, + { + "task_id": 339, + "ok": false + }, + { + "task_id": 340, + "ok": true + }, + { + "task_id": 341, + "ok": true + }, + { + "task_id": 342, + "ok": false + }, + { + "task_id": 343, + "ok": true + }, + { + "task_id": 344, + "ok": true + }, + { + "task_id": 345, + "ok": true + }, + { + "task_id": 346, + "ok": false + }, + { + "task_id": 347, + "ok": true + }, + { + "task_id": 348, + "ok": false + }, + { + "task_id": 349, + "ok": true + }, + { + "task_id": 350, + "ok": true + }, + { + "task_id": 351, + "ok": false + }, + { + "task_id": 352, + "ok": true + }, + { + "task_id": 353, + "ok": true + }, + { + "task_id": 354, + "ok": true + }, + { + "task_id": 355, + "ok": false + }, + { + "task_id": 356, + "ok": true + }, + { + "task_id": 357, + "ok": true + }, + { + "task_id": 358, + "ok": true + }, + { + "task_id": 359, + "ok": false + }, + { + "task_id": 360, + "ok": false + }, + { + "task_id": 361, + "ok": true + }, + { + "task_id": 362, + "ok": false + }, + { + "task_id": 363, + "ok": true + }, + { + "task_id": 364, + "ok": true + }, + { + "task_id": 365, + "ok": true + }, + { + "task_id": 366, + "ok": true + }, + { + "task_id": 367, + "ok": false + }, + { + "task_id": 368, + "ok": true + }, + { + "task_id": 369, + "ok": false + }, + { + "task_id": 370, + "ok": false + }, + { + "task_id": 371, + "ok": false + }, + { + "task_id": 372, + "ok": true + }, + { + "task_id": 373, + "ok": true + }, + { + "task_id": 374, + "ok": false + }, + { + "task_id": 375, + "ok": false + }, + { + "task_id": 376, + "ok": false + }, + { + "task_id": 377, + "ok": true + }, + { + "task_id": 378, + "ok": true + }, + { + "task_id": 379, + "ok": true + }, + { + "task_id": 380, + "ok": false + }, + { + "task_id": 381, + "ok": true + }, + { + "task_id": 382, + "ok": false + }, + { + "task_id": 383, + "ok": false + }, + { + "task_id": 384, + "ok": false + }, + { + "task_id": 385, + "ok": true + }, + { + "task_id": 386, + "ok": false + }, + { + "task_id": 387, + "ok": true + }, + { + "task_id": 388, + "ok": true + }, + { + "task_id": 389, + "ok": true + }, + { + "task_id": 390, + "ok": false + }, + { + "task_id": 391, + "ok": true + }, + { + "task_id": 392, + "ok": false + }, + { + "task_id": 393, + "ok": true + }, + { + "task_id": 394, + "ok": true + }, + { + "task_id": 395, + "ok": true + }, + { + "task_id": 396, + "ok": false + }, + { + "task_id": 397, + "ok": true + }, + { + "task_id": 398, + "ok": false + }, + { + "task_id": 399, + "ok": true + }, + { + "task_id": 400, + "ok": false + }, + { + "task_id": 401, + "ok": true + }, + { + "task_id": 402, + "ok": false + }, + { + "task_id": 403, + "ok": false + }, + { + "task_id": 404, + "ok": true + }, + { + "task_id": 405, + "ok": true + }, + { + "task_id": 406, + "ok": true + }, + { + "task_id": 407, + "ok": false + }, + { + "task_id": 408, + "ok": false + }, + { + "task_id": 409, + "ok": true + }, + { + "task_id": 410, + "ok": false + }, + { + "task_id": 411, + "ok": true + }, + { + "task_id": 412, + "ok": true + }, + { + "task_id": 413, + "ok": true + }, + { + "task_id": 414, + "ok": true + }, + { + "task_id": 415, + "ok": false + }, + { + "task_id": 416, + "ok": false + }, + { + "task_id": 417, + "ok": false + }, + { + "task_id": 418, + "ok": true + }, + { + "task_id": 419, + "ok": true + }, + { + "task_id": 420, + "ok": true + }, + { + "task_id": 421, + "ok": true + }, + { + "task_id": 422, + "ok": true + }, + { + "task_id": 423, + "ok": false + }, + { + "task_id": 424, + "ok": true + }, + { + "task_id": 425, + "ok": true + }, + { + "task_id": 426, + "ok": true + }, + { + "task_id": 427, + "ok": true + }, + { + "task_id": 428, + "ok": true + }, + { + "task_id": 429, + "ok": true + }, + { + "task_id": 430, + "ok": false + }, + { + "task_id": 431, + "ok": true + }, + { + "task_id": 432, + "ok": false + }, + { + "task_id": 433, + "ok": true + }, + { + "task_id": 434, + "ok": true + }, + { + "task_id": 435, + "ok": true + }, + { + "task_id": 436, + "ok": false + }, + { + "task_id": 437, + "ok": true + }, + { + "task_id": 438, + "ok": false + }, + { + "task_id": 439, + "ok": true + }, + { + "task_id": 440, + "ok": false + }, + { + "task_id": 441, + "ok": true + }, + { + "task_id": 442, + "ok": false + }, + { + "task_id": 443, + "ok": false + }, + { + "task_id": 444, + "ok": false + }, + { + "task_id": 445, + "ok": true + }, + { + "task_id": 446, + "ok": true + }, + { + "task_id": 447, + "ok": true + }, + { + "task_id": 448, + "ok": false + }, + { + "task_id": 449, + "ok": false + }, + { + "task_id": 450, + "ok": true + }, + { + "task_id": 451, + "ok": true + }, + { + "task_id": 452, + "ok": true + }, + { + "task_id": 453, + "ok": true + }, + { + "task_id": 454, + "ok": true + }, + { + "task_id": 455, + "ok": true + }, + { + "task_id": 456, + "ok": true + }, + { + "task_id": 457, + "ok": true + }, + { + "task_id": 458, + "ok": true + }, + { + "task_id": 459, + "ok": true + }, + { + "task_id": 460, + "ok": true + }, + { + "task_id": 461, + "ok": false + }, + { + "task_id": 462, + "ok": false + }, + { + "task_id": 463, + "ok": true + }, + { + "task_id": 464, + "ok": true + }, + { + "task_id": 465, + "ok": true + }, + { + "task_id": 466, + "ok": true + }, + { + "task_id": 467, + "ok": false + }, + { + "task_id": 468, + "ok": false + }, + { + "task_id": 469, + "ok": false + }, + { + "task_id": 470, + "ok": true + }, + { + "task_id": 471, + "ok": true + }, + { + "task_id": 472, + "ok": false + }, + { + "task_id": 473, + "ok": false + }, + { + "task_id": 474, + "ok": true + }, + { + "task_id": 475, + "ok": true + }, + { + "task_id": 476, + "ok": true + }, + { + "task_id": 477, + "ok": true + }, + { + "task_id": 478, + "ok": true + }, + { + "task_id": 479, + "ok": true + }, + { + "task_id": 480, + "ok": false + }, + { + "task_id": 481, + "ok": false + }, + { + "task_id": 482, + "ok": true + }, + { + "task_id": 483, + "ok": false + }, + { + "task_id": 484, + "ok": true + }, + { + "task_id": 485, + "ok": true + }, + { + "task_id": 486, + "ok": false + }, + { + "task_id": 487, + "ok": true + }, + { + "task_id": 488, + "ok": false + }, + { + "task_id": 489, + "ok": false + }, + { + "task_id": 490, + "ok": false + }, + { + "task_id": 491, + "ok": true + }, + { + "task_id": 492, + "ok": true + }, + { + "task_id": 493, + "ok": false + }, + { + "task_id": 494, + "ok": false + }, + { + "task_id": 495, + "ok": true + }, + { + "task_id": 496, + "ok": true + }, + { + "task_id": 497, + "ok": false + }, + { + "task_id": 498, + "ok": true + }, + { + "task_id": 499, + "ok": true + }, + { + "task_id": 500, + "ok": false + }, + { + "task_id": 501, + "ok": false + }, + { + "task_id": 502, + "ok": true + }, + { + "task_id": 503, + "ok": false + }, + { + "task_id": 504, + "ok": true + }, + { + "task_id": 505, + "ok": true + }, + { + "task_id": 506, + "ok": true + }, + { + "task_id": 507, + "ok": true + }, + { + "task_id": 508, + "ok": true + }, + { + "task_id": 509, + "ok": true + }, + { + "task_id": 510, + "ok": false + } + ] +} \ No newline at end of file diff --git a/results-loop/eval_bestof3_select.json b/results-loop/eval_bestof3_select.json new file mode 100644 index 0000000..4fdbdfb --- /dev/null +++ b/results-loop/eval_bestof3_select.json @@ -0,0 +1,3016 @@ +{ + "oracle_acc": 0.578, + "selected_acc": 0.55, + "oracle_by_label": { + "easy": 0.9884615384615385, + "hard": 0.34545454545454546, + "drop": 0.07027027027027027 + }, + "selected_by_label": { + "easy": 0.9769230769230769, + "hard": 0.2727272727272727, + "drop": 0.032432432432432434 + }, + "per_item": [ + { + "task_id": 11, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 12, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 13, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 14, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 15, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 16, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 17, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 18, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 19, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 20, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 21, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 22, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 23, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 24, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 25, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 26, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 27, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 28, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 29, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 30, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 31, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 32, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 33, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 34, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 35, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 36, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 37, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 38, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 39, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 40, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 41, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 42, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 43, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 44, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 45, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 46, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 47, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 48, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 49, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 50, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 51, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 52, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 53, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 54, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 55, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 56, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 57, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 58, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 59, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 60, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 61, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 62, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 63, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 64, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 65, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 66, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 67, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 68, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 69, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 70, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 71, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 72, + "oracle": true, + "selected": false, + "label": "hard" + }, + { + "task_id": 73, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 74, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 75, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 76, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 77, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 78, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 79, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 80, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 81, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 82, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 83, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 84, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 85, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 86, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 87, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 88, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 89, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 90, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 91, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 92, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 93, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 94, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 95, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 96, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 97, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 98, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 99, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 100, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 101, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 102, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 103, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 104, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 105, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 106, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 107, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 108, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 109, + "oracle": true, + "selected": false, + "label": "hard" + }, + { + "task_id": 110, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 111, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 112, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 113, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 114, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 115, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 116, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 117, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 118, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 119, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 120, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 121, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 122, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 123, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 124, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 125, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 126, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 127, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 128, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 129, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 130, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 131, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 132, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 133, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 134, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 135, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 136, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 137, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 138, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 139, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 140, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 141, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 142, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 143, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 144, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 145, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 146, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 147, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 148, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 149, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 150, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 151, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 152, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 153, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 154, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 155, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 156, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 157, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 158, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 159, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 160, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 161, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 162, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 163, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 164, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 165, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 166, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 167, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 168, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 169, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 170, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 171, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 172, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 173, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 174, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 175, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 176, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 177, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 178, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 179, + "oracle": true, + "selected": false, + "label": "easy" + }, + { + "task_id": 180, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 181, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 182, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 183, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 184, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 185, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 186, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 187, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 188, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 189, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 190, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 191, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 192, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 193, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 194, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 195, + "oracle": true, + "selected": false, + "label": "hard" + }, + { + "task_id": 196, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 197, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 198, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 199, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 200, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 201, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 202, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 203, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 204, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 205, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 206, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 207, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 208, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 209, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 210, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 211, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 212, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 213, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 214, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 215, + "oracle": true, + "selected": false, + "label": "hard" + }, + { + "task_id": 216, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 217, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 218, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 219, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 220, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 221, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 222, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 223, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 224, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 225, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 226, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 227, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 228, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 229, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 230, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 231, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 232, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 233, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 234, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 235, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 236, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 237, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 238, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 239, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 240, + "oracle": true, + "selected": false, + "label": "easy" + }, + { + "task_id": 241, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 242, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 243, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 244, + "oracle": false, + "selected": false, + "label": "easy" + }, + { + "task_id": 245, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 246, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 247, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 248, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 249, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 250, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 251, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 252, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 253, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 254, + "oracle": true, + "selected": false, + "label": "easy" + }, + { + "task_id": 255, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 256, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 257, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 258, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 259, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 260, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 261, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 262, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 263, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 264, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 265, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 266, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 267, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 268, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 269, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 270, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 271, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 272, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 273, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 274, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 275, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 276, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 277, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 278, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 279, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 280, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 281, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 282, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 283, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 284, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 285, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 286, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 287, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 288, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 289, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 290, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 291, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 292, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 293, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 294, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 295, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 296, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 297, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 298, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 299, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 300, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 301, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 302, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 303, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 304, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 305, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 306, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 307, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 308, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 309, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 310, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 311, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 312, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 313, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 314, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 315, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 316, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 317, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 318, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 319, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 320, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 321, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 322, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 323, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 324, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 325, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 326, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 327, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 328, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 329, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 330, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 331, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 332, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 333, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 334, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 335, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 336, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 337, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 338, + "oracle": false, + "selected": false, + "label": "easy" + }, + { + "task_id": 339, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 340, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 341, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 342, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 343, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 344, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 345, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 346, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 347, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 348, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 349, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 350, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 351, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 352, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 353, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 354, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 355, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 356, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 357, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 358, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 359, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 360, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 361, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 362, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 363, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 364, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 365, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 366, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 367, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 368, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 369, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 370, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 371, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 372, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 373, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 374, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 375, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 376, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 377, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 378, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 379, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 380, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 381, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 382, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 383, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 384, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 385, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 386, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 387, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 388, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 389, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 390, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 391, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 392, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 393, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 394, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 395, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 396, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 397, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 398, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 399, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 400, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 401, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 402, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 403, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 404, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 405, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 406, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 407, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 408, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 409, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 410, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 411, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 412, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 413, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 414, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 415, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 416, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 417, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 418, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 419, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 420, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 421, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 422, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 423, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 424, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 425, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 426, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 427, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 428, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 429, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 430, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 431, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 432, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 433, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 434, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 435, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 436, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 437, + "oracle": true, + "selected": false, + "label": "drop" + }, + { + "task_id": 438, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 439, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 440, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 441, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 442, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 443, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 444, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 445, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 446, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 447, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 448, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 449, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 450, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 451, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 452, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 453, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 454, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 455, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 456, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 457, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 458, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 459, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 460, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 461, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 462, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 463, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 464, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 465, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 466, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 467, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 468, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 469, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 470, + "oracle": true, + "selected": true, + "label": "drop" + }, + { + "task_id": 471, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 472, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 473, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 474, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 475, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 476, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 477, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 478, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 479, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 480, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 481, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 482, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 483, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 484, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 485, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 486, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 487, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 488, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 489, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 490, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 491, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 492, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 493, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 494, + "oracle": false, + "selected": false, + "label": "hard" + }, + { + "task_id": 495, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 496, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 497, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 498, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 499, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 500, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 501, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 502, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 503, + "oracle": false, + "selected": false, + "label": "drop" + }, + { + "task_id": 504, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 505, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 506, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 507, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 508, + "oracle": true, + "selected": true, + "label": "hard" + }, + { + "task_id": 509, + "oracle": true, + "selected": true, + "label": "easy" + }, + { + "task_id": 510, + "oracle": false, + "selected": false, + "label": "easy" + } + ] +} \ No newline at end of file diff --git a/results-loop/stats_final.json b/results-loop/stats_final.json index 2a7234a..6f2454d 100644 --- a/results-loop/stats_final.json +++ b/results-loop/stats_final.json @@ -322,6 +322,108 @@ "a_only": 0, "b_only": 4, "p": 0.125 + }, + "bo3-oracle vs loop k=4, overall": { + "n": 500, + "a_only": 27, + "b_only": 48, + "p": 0.020298406990107445 + }, + "bo3-oracle vs loop k=4, hard": { + "n": 55, + "a_only": 14, + "b_only": 9, + "p": 0.4048728942871094 + }, + "bo3-oracle vs distill k=1, overall": { + "n": 500, + "a_only": 27, + "b_only": 44, + "p": 0.056814677932839015 + }, + "bo3-oracle vs distill k=1, hard": { + "n": 55, + "a_only": 14, + "b_only": 10, + "p": 0.5412561893463135 + }, + "bo3-deployable vs loop k=4, overall": { + "n": 500, + "a_only": 31, + "b_only": 38, + "p": 0.4703685318581444 + }, + "bo3-deployable vs loop k=4, hard": { + "n": 55, + "a_only": 16, + "b_only": 7, + "p": 0.0931396484375 + }, + "bo3-deployable vs distill k=1, overall": { + "n": 500, + "a_only": 31, + "b_only": 34, + "p": 0.8043170001933986 + }, + "bo3-deployable vs distill k=1, hard": { + "n": 55, + "a_only": 15, + "b_only": 7, + "p": 0.13380050659179688 + } + }, + "best-of-3 ORACLE (any-pass)": { + "overall": { + "acc": 0.578, + "n": 500, + "ci": [ + 0.534, + 0.621 + ] + }, + "hard": { + "acc": 0.34545454545454546, + "n": 55, + "ci": [ + 0.234, + 0.477 + ] + } + }, + "best-of-3 oracle (selector run)": { + "overall": { + "acc": 0.578, + "n": 500, + "ci": [ + 0.534, + 0.621 + ] + }, + "hard": { + "acc": 0.34545454545454546, + "n": 55, + "ci": [ + 0.234, + 0.477 + ] + } + }, + "best-of-3 DEPLOYABLE (logprob-selected)": { + "overall": { + "acc": 0.55, + "n": 500, + "ci": [ + 0.506, + 0.593 + ] + }, + "hard": { + "acc": 0.2727272727272727, + "n": 55, + "ci": [ + 0.173, + 0.402 + ] } }, "pooled_hard_loop": { diff --git a/scripts/stats_final.py b/scripts/stats_final.py index cf09c16..56833f6 100644 --- a/scripts/stats_final.py +++ b/scripts/stats_final.py @@ -200,6 +200,45 @@ def main(): lines.append(f"- {name}: A-only {r['a_only']}, B-only {r['b_only']}, " f"n={r['n']}, p={r['p']:.4g} ({sig})") + # ---------- 2b. token baselines, per-item (oracle vs deployable) ------ + try: + d = json.load(open(OUT / "eval_bestof3_select.json")) + sel = {it["task_id"]: it["selected"] for it in d["per_item"]} + orc = {it["task_id"]: it["oracle"] for it in d["per_item"]} + d2 = json.load(open(OUT / "eval_bestof3_pi.json")) + orc_pi = {it["task_id"]: it["ok"] for it in d2["per_item"]} + lines += ["", "## Token baselines (paired, per-item)", ""] + for name, m in [("best-of-3 ORACLE (any-pass)", orc_pi), + ("best-of-3 oracle (selector run)", orc), + ("best-of-3 DEPLOYABLE (logprob-selected)", sel)]: + o, h = acc_ci(m), acc_ci(m, mbpp_hard) + lines.append(f"- **{name}**: overall {fmt(o)}; hard {fmt(h)}") + report[name] = {"overall": o, "hard": h} + for base_name, m in [("oracle", orc_pi), ("deployable", sel)]: + for arm_name, arm in [("loop k=4", loop4), ("distill k=1", dist1)]: + for sub, subn in [(None, "overall"), (mbpp_hard, "hard")]: + r = mcnemar(pair(arm, m, sub)) + report["mcnemar"][f"bo3-{base_name} vs {arm_name}, {subn}"] = r + sig = "**significant**" if r["p"] < 0.05 else "n.s." + lines.append(f"- bo3-{base_name} vs {arm_name}, {subn}: " + f"arm-only {r['a_only']}, bo3-only " + f"{r['b_only']}, p={r['p']:.4g} ({sig})") + d3 = json.load(open(OUT / "eval_budgetcot_pi.json")) + bc = {it["task_id"]: it["ok"] for it in d3["per_item"]} + o, h = acc_ci(bc), acc_ci(bc, mbpp_hard) + lines.append(f"- **budget-CoT-50 (per-item rerun)**: overall {fmt(o)}; " + f"hard {fmt(h)}") + for arm_name, arm in [("loop k=4", loop4), ("distill k=1", dist1)]: + for sub, subn in [(None, "overall"), (mbpp_hard, "hard")]: + r = mcnemar(pair(arm, bc, sub)) + report["mcnemar"][f"budget-cot vs {arm_name}, {subn}"] = r + sig = "**significant**" if r["p"] < 0.05 else "n.s." + lines.append(f"- budget-CoT vs {arm_name}, {subn}: arm-only " + f"{r['a_only']}, cot-only {r['b_only']}, " + f"p={r['p']:.4g} ({sig})") + except FileNotFoundError as e: + lines.append(f"(token-baseline per-item files incomplete: {e})") + # ---------- 3. pooled hard bucket across benchmarks ---------- lines += ["", "## Pooled hard bucket (MBPP + HumanEval + Rust)", "", "Paired within-item k>0 vs k=0, counts pooled across "