Update TODO.md with Exp 3 full PCA/SVD results

TODO.md

@@ -1,9 +1,9 @@
 # NeuroGolf Solver — Roadmap
 
-> Current: v5.0 · 50 arc-gen validated (v4 baseline) · ~670 LB · Target: 3000+
+> Current: v5.1 · 49 arc-gen validated (budget=5s) · ~603.6 score · Target: 3000+
 > Philosophy: **Research → Design → Experiment → Analyze → Research** loop until confirmed score increase.
 > Rule: **NEVER claim a feature works without full arc-gen validation on representative tasks.**
-> Updated: 2026-04-26 — Phase 2 experiments tested. Overfitting hypothesis REFUTED. Architecture mismatch identified as root cause.
+> Updated: 2026-04-26 — Exp 3 (PCA/SVD) fully tested on 400 tasks. 0 PCR solves. Architecture mismatch confirmed.
 
 ---
 
@@ -36,184 +36,98 @@
 
 ---
 
-## Phase 2: Fix Arc-Gen Survival — THE #1 BLOCKER
+## Phase 2: Fix Arc-Gen Survival — EXPERIMENTS COMPLETED
 
-> **Status:** 307 solved locally, only 50 survive arc-gen. ~250 tasks affected by lstsq overfitting.
-> **Root cause confirmed by literature:** catastrophic overfitting at the interpolation threshold (p ≈ n).
-> **Strategy:** Coordinated experiment sequence — each builds on the previous. Do NOT test in isolation.
+> **Status:** Exps 0-3 tested. Root cause is architecture mismatch, not regularization.
+> **Action:** Move to Phase 3 (new solver types). Keep PCR code for future Lasso/Ridge experiments.
 
 ### The Problem (with numbers from conv.py)
 
-Current `_lstsq_conv()` runs naked `np.linalg.lstsq(P, T_oh, rcond=None)` — zero regularization.
-Kernel search is `[1, 3, 5, 7, 9, 11, ...]`, stops at **first ks that interpolates training**.
+Current `_lstsq_conv()` runs `np.linalg.lstsq(P, T_oh, rcond=None)` — zero regularization.
+v5.1 refactored to composable primitives: `_build_patch_matrix` + `_solve_weights` + `_extract_weights`.
+PCR (`_solve_weights_pcr`) added as deferred 2nd-pass fallback.
 
 | Kernel | p (features) | n (patches, 7×7 grid, 4 ex) | p/n | Regime |
 |--------|-------------|------------------------------|-----|--------|
 | ks=1 | 10 | 196 | 0.05 | ✅ Safe underparameterized |
 | ks=3 | 90 | 196 | 0.46 | ✅ Underparameterized |
 | **ks=5** | **250** | **196** | **1.27** | **❌ INTERPOLATION THRESHOLD** |
-| **ks=7** | **490** | **196** | **2.50** | **❌ PAST THRESHOLD — WORST CASE** |
-| **ks=9** | **810** | **196** | **4.13** | **⚠️ Near peak** |
+| **ks=7** | **490** | **196** | **2.50** | **❌ PAST THRESHOLD** |
 | ks=11 | 1210 | 196 | 6.17 | Overparameterized |
 | ks=29 | 8410 | 196 | 42.9 | Heavily overparameterized |
 
-The solver accepts ks=5 (which perfectly interpolates training via minimum-norm solution) and **never tries ks=11+** which might actually generalize.
-
 ### Literature Backing
 
 | Paper | arxiv | Key Finding for Us |
 |-------|-------|--------------------|
-| Nakkiran et al. 2019 (NeurIPS) | `1912.02292` | Test error peaks at p≈n (interpolation threshold). This is exactly where ks=5,7 sit. Skipping these eliminates the peak entirely. |
-| Segert 2023 | `2311.11093` | Truncated SVD / PCA regression achieves flatter loss basins than Ridge. Optimal for low-rank covariance (our case: effective rank ~10-40). |
-| Zhou & Ge 2023 (NeurIPS) | `2302.00257` | L1 (Lasso) achieves near-minimax for sparse β*. L2 (Ridge) cannot. ARC one-hot patches are sparse (3-5 of 10 channels active). |
-| Liu et al. 2023 | `2302.01088` | More fitting rows help ONLY with regularization. Without it, adding rows near threshold can *hurt* (sample-wise non-monotonicity). |
-| Ali et al. 2019 | — | GD with early stopping ≡ Ridge with λ=1/(2t). Since Ridge is suboptimal here, GD early stopping is also suboptimal. |
-| Liao & Gu 2024 (CompressARC) | `2512.06104` | ARC solvers that generalize use regularized fitting (MDL/KL), not ridgeless interpolation. Direct evidence regularization is needed. |
-
-### Coordinated Experiment Sequence
+| Nakkiran et al. 2019 (NeurIPS) | `1912.02292` | Test error peaks at p≈n. Correct theory but inapplicable — tasks fail for architecture mismatch, not regularization. |
+| Segert 2023 | `2311.11093` | PCA > Ridge for low-rank covariance. Tested: 0/400 PCR solves. Signal is in the noise dimensions PCA removes. |
+| Zhou & Ge 2023 (NeurIPS) | `2302.00257` | L1 near-minimax for sparse signals. **Untested** — may still help for Exp 5. |
+| Liao & Gu 2024 (CompressARC) | `2512.06104` | Regularization enables ARC generalization. True in their framework (MDL/KL) but conv lstsq is a different beast. |
 
-> Run in order. Each experiment keeps wins from previous experiments.
-> **Goal: highest-scoring valid model per task**, not first-valid.
+### Experiment Results
 
----
+#### Exp 0: Baseline Measurement [-] DONE
+- v5.0 on 400 tasks with budget=5s: **49 solved, 603.6 score**
+- Conv breakdown: 16 conv_var + 8 conv_fixed + 1 conv_diff = 25 conv tasks
 
-#### Exp 0: Baseline Measurement ⬜
-> *Prerequisite for all other experiments.*
+#### Exp 1: Skip ks=5,7,9 [-] REJECTED
+- HURTS 2 solved tasks (322@ks5, 299@ks9), helps 0 new
 
-- [ ] Run current v5 on all 400 tasks with full arc-gen validation
-- [ ] Record per-task: (a) solver used, (b) ks chosen, (c) arc-gen pass/fail, (d) score, (e) p/n ratio
-- [ ] Identify the ~250 tasks that fail arc-gen — classify by ks and p/n ratio
-- **Exit criteria:** Have baseline numbers to compare against
-
----
+#### Exp 2: Best-of-N [~] NEUTRAL
+- No new solves on unsolved tasks. Score optimization only.
 
-#### Exp 1: Skip ks=5,7,9 ⬜ — Confidence: **90%**
-> *1 line change per solver. Eliminates the interpolation threshold peak entirely.*
+#### Exp 3: PCA / Truncated SVD [-] REJECTED — Confidence: ~~75%~~ → **0%**
 
-**Evidence:** Nakkiran 2019 (`1912.02292`) proves test error peaks at p≈n. Our ks=5 (p=250, n≈196) is textbook worst-case. Removing these kernel sizes cannot make things worse — if a task *needs* ks=5 to solve, it was going to fail arc-gen anyway because it's in the catastrophic regime.
-
-**10% doubt:** Some tasks with large grids (21×21, 16 examples → n≈7056) have p/n < 1 even at ks=7. For those, ks=7 is safe. But the solver can't distinguish these cases without computing p/n per-task.
-
-- [ ] Change ks list in all 4 conv solvers: `[1, 3, 5, 7, 9, 11, ...]` → `[1, 3, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29]`
-  - Files: `conv.py` — `solve_conv_fixed`, `solve_conv_variable`, `solve_conv_diffshape`, `solve_conv_var_diff`
-- [ ] Run all 400 with arc-gen. Compare survival rate vs Exp 0.
-- **Accept if:** arc-gen survival improves by ≥5 tasks
-- **Expected:** +10-30 tasks
-
----
+**Full test results (2026-04-26):**
 
-#### Exp 2: Best-of-N Model Selection ⬜ — Confidence: **85%**
-> *Structural change to solve loop. Return highest-scoring valid model, not first-valid.*
-
-**Evidence:** Pure engineering — no theoretical uncertainty. Currently `conv.py` iterates ks smallest-first and returns the first that passes validation. This means if ks=3 AND ks=13 both pass arc-gen, we might return ks=13 (tried first due to bias loop) when ks=3 scores higher (lower MACs). Score = max(1, 25 - ln(cost)), so smaller models always score higher.
-
-**15% doubt:** Runtime. Trying all 12 kernel sizes × 2 bias options × arc-gen validation = up to 24 candidates per task. May blow the 12hr Kaggle time budget. Mitigate: set tighter per-candidate timeout, parallelize validation.
-
-- [ ] Refactor `solve_conv_*` to return **list of (model, ks, cost)** candidates instead of first-valid
-- [ ] Refactor `solve_task` to collect all candidates (analytical + all conv variants), pick cheapest valid
-- [ ] Add static cost estimation to pick cheapest before saving
-- [ ] Run all 400. Compare total score vs Exp 1.
-- **Accept if:** total score improves by ≥3% on existing solved tasks
-- **Expected:** +5-15 score points on tasks already solved (better model selection)
-
----
-
-#### Exp 3: PCA / Truncated SVD Before lstsq ⬜ — Confidence: **75%**
-> *~30 lines in `_lstsq_conv()`. Maps every ks into effective underparameterized regime.*
-
-**Evidence:** Segert 2023 (`2311.11093`) — PCA regression is provably better than Ridge for low-rank covariance. Our patch covariance has effective rank ~10-40 (few active colors in one-hot encoding). Truncating to top-k components removes the ~(p-40) pure noise dimensions that ridgeless lstsq amplifies into catastrophic overfitting.
-
-**25% doubt:** The variance threshold (99%) might be wrong for some tasks. Too aggressive truncation (k too small) kills signal. Too little (k too large) doesn't fix the problem. Need per-task adaptive k based on singular value gap.
-
-**Implementation:**
-```python
-def _lstsq_pcr(P, T_oh, var_threshold=0.99):
-    U, s, Vt = np.linalg.svd(P, full_matrices=False)
-    cumvar = np.cumsum(s**2) / np.sum(s**2)
-    k = np.searchsorted(cumvar, var_threshold) + 1
-    k = max(k, 5)  # floor: keep at least 5 components
-    P_red = U[:, :k] * s[:k]  # n × k, always k << n
-    w_red = np.linalg.lstsq(P_red, T_oh, rcond=None)[0]
-    w_full = Vt[:k].T @ w_red  # back to p-dim for ONNX weights
-    return w_full
-```
-
-- [ ] Add `_lstsq_pcr()` to `conv.py` alongside existing `_lstsq_conv()`
-- [ ] Use PCA path for all ks where p/n > 0.5 (safe margin below threshold)
-- [ ] Keep raw lstsq for ks=1,3 where p << n (PCA unnecessary, adds cost)
-- [ ] Try var_threshold in {0.95, 0.99, 0.999} — pick best per arc-gen survival
-- [ ] Run all 400. Compare survival rate vs Exp 1.
-- **Accept if:** arc-gen survival improves by ≥10 tasks vs Exp 1
-- **Expected:** +15-40 tasks (the big win — makes previously-impossible ks usable)
-
----
+**Diagnostic on 25 solved conv tasks:**
+| p/n regime | Tasks | PCR at 0.99 | Arc-gen impact |
+|------------|-------|-------------|----------------|
+| p/n < 0.5 (safe) | 17 | Mostly fits train | Already 100% ag — no improvement possible |
+| p/n > 1.0 (danger) | 8 | 4 fail to fit train at ANY threshold | PCR removes dimensions that carry signal |
 
-#### Exp 4: Increase Arc-Gen Fitting Cap ⬜ — Confidence: **60%**
-> *1 line change. Only works WITH regularization (PCA) in place.*
+**Diagnostic on 345 unsolved tasks (same-shape only, ks≤9):**
+- Only **10 tasks** have any ks where lstsq fits training
+- PCR improves arc-gen accuracy on **4 tasks** (by 3-9%) but **none reach 100%** required for validation
+  - Task 32: lstsq 87.5% → PCR 94.9% (still fails)
+  - Task 389: lstsq 87.2% → PCR 95.7% (still fails)
+  - Task 129: lstsq 59.6% → PCR 63.0% (still fails)
+  - Task 229: lstsq 57.0% → PCR 60.0% (still fails)
 
-**Evidence:** Liu et al. 2023 (`2302.01088`) — more fitting rows help only in regularized regime. With PCA, more rows = more constraints in the reduced k-dimensional space = better conditioning. Without PCA, adding rows to underdetermined lstsq doesn't fix the fundamental problem.
+**Full 400-task run with PCR-enhanced solver:**
+- 50 solved (vs 49 baseline) — the +1 is Task 61, a **timing artifact** (took 11.8s, not a PCR solve)
+- **0 tasks solved via PCR path**
+- **0 regressions** on existing 25 conv tasks
+- Code kept: composable primitives useful for future Lasso/Ridge experiments
 
-**40% doubt:** Arc-gen examples may have different grid sizes (filtered out by `get_exs_for_fitting`). The cap increase only helps if enough same-shape arc-gen examples exist.
+**Why PCR failed:**
+1. For tasks with p/n < 0.5: lstsq already generalizes perfectly. PCR is unnecessary.
+2. For tasks with p/n > 1.0: the training signal requires ALL patch dimensions to interpolate. PCA truncation removes exactly the dimensions that encode the (noisy) signal, causing train_fail.
+3. For unsolved tasks: most (~335/345) can't be fit by ANY ks — architecture mismatch (conv can't represent the required operation). The 10 that fit have wrong arc-gen behavior because the task requires global reasoning, not local patches.
 
-- [ ] Change `get_exs_for_fitting()`: cap 10 → 50
-- [ ] Change `get_exs_for_fitting_variable()`: cap 20 → 100
-- [ ] Run all 400. Compare vs Exp 3.
-- **Accept if:** arc-gen survival improves by ≥3 tasks vs Exp 3
-- **Expected:** +5-15 tasks (modest but free)
-
----
+#### Exp 4: Increase Arc-Gen Fitting Cap [DEPRIORITIZED]
+> Only works with regularization. Since regularization (Exp 3) didn't help, this is moot.
 
 #### Exp 5: Lasso (L1) for Large Kernels ⬜ — Confidence: **55%**
-> *~15 lines + sklearn dependency. Better than L2 for sparse signals, but slower and fragile.*
-
-**Evidence:** Zhou & Ge 2023 (`2302.00257`) — L1 achieves near-minimax O(σ²·s·log(d/s)/n) for sparse β*, vs Ridge's Ω(‖β*‖²). ARC one-hot patches are sparse (3-5 of 10 channels active). Segert 2023 Section A.10: Lasso competitive with PCA/Nuclear in sparse regime, wins ~40% of cases.
-
-**45% doubt:** (1) Lasso is slow — coordinate descent vs single SVD. (2) `alpha` tuning via CV with only 4-6 training examples is fragile. (3) Need `MultiTaskLassoCV` for 10-column one-hot target, not scalar `LassoCV`. (4) sklearn adds a dependency (not available on Kaggle by default — need to verify).
-
-- [ ] Add `_lstsq_lasso()` using `sklearn.linear_model.MultiTaskLassoCV`
-- [ ] Use Lasso only for ks≥11 where p > n even after PCA (complement, not replacement)
-- [ ] Verify sklearn available on Kaggle runtime
-- [ ] Run all 400. Compare vs Exp 3+4.
-- **Accept if:** arc-gen survival improves by ≥5 tasks vs Exp 3+4
-- **Expected:** +5-10 tasks (incremental over PCA)
-
----
-
-#### Exp 6 [DEPRIORITIZED]: GD with Early Stopping ⬜ — Confidence: **40%**
-> *Moved to backlog. Literature shows GD early stopping ≡ Ridge (Ali et al. 2019), which is suboptimal for our low-rank regime. Only revisit if Exp 1-5 plateau.*
+> Still potentially useful — L1 selects sparse features differently from PCA. Untested.
+> But given that only 10/345 unsolved tasks even have lstsq fits, the ceiling is very low.
 
-- [ ] Only attempt if Exp 1-5 combined yield <80 arc-gen validated tasks
-- [ ] If attempted: use `sklearn.linear_model.SGDRegressor` with `early_stopping=True`
+#### Exp 6-8: [DEPRIORITIZED]
 
 ---
 
-#### Exp 7 [DEPRIORITIZED]: PyTorch Multi-Seed (GPU Required) ⬜ — Confidence: **50%**
-> *Needs GPU, slow, complex. Only after simpler fixes validated.*
+### Phase 2 Post-Mortem
 
-- [!] Blocked on GPU availability
-- [ ] Only attempt if Exp 1-5 combined yield <100 arc-gen validated tasks
+**Original projection was wildly optimistic:**
+| Scenario | Projected | Actual |
+|----------|-----------|--------|
+| Exp 1 alone | 60-80 tasks | **HURT** 2 tasks |
+| Exp 1+2+3 | 90-130 tasks | **49 tasks** (no change) |
 
----
-
-#### Exp 8 [DEPRIORITIZED]: Generate More ARC-GEN Data ⬜ — Confidence: **45%**
-> *Only useful WITH regularization in place (Exp 3+). Without it, more rows can *hurt* (Nakkiran 2019 sample-wise non-monotonicity).*
-
-- [ ] Only attempt after Exp 4 to see if cap increase helped
-- [ ] If yes: generate 1000+ examples/task using ARC-GEN generator
-
----
-
-### Phase 2 Combined Projection
+**Root cause confirmed:** Architecture mismatch, not regularization. The ~300 unsolved tasks require operations (mode counting, flood fill, outline detection, pattern matching) that NO local convolution can represent, regardless of regularization.
 
-| Scenario | Expected arc-gen tasks | LB estimate | Confidence |
-|----------|----------------------|-------------|------------|
-| Exp 1 alone (skip ks) | 60-80 | ~800-1000 | 90% |
-| Exp 1+2 (skip + best-of-N) | 60-80 tasks, better scores | ~900-1100 | 85% |
-| Exp 1+2+3 (+ PCA) | 90-130 | ~1200-1700 | 70% |
-| Exp 1+2+3+4 (+ more arc-gen) | 100-140 | ~1400-1900 | 60% |
-| Full stack 1-5 (+ Lasso) | 110-150 | ~1600-2200 | 50% |
-
-**The big win is the Exp 1+2+3 stack.** Skip bad kernels, pick best model, PCA regularization. If those three work, we roughly double or triple the LB score.
+**Next steps:** Phase 3 (new solver types) or new architectures. The conv solver has reached its ceiling at ~25 tasks.
 
 ---
 
@@ -254,8 +168,6 @@ def _lstsq_pcr(P, T_oh, var_threshold=0.99):
 - [ ] **Validate**: Compare static profiler vs onnx_tool on 50 random models.
   - Accept if divergence >5% and fix profiler.
 
-> **Note:** Best-of-N model selection moved to Phase 2 Exp 2 — it's part of the core overfitting fix, not just optimization.
-
 ---
 
 ## BLENDING — EXPLICITLY EXCLUDED
@@ -278,24 +190,29 @@ Competitive intelligence on blending stays in LEARNING.md "What Others Do" secti
 | 2026-04-25 | v5 untested code | 10 | 3/10 FAILED arc-gen | **REVERTED** |
 | 2026-04-26 | v5.0 refactor | 394 | **49 solved, ~603.6 score, budget=5s** | New baseline |
 | 2026-04-26 | Exp 0: Baseline | 25 conv tasks | 24/25 solved, score=253 | Baseline for conv |
-| 2026-04-26 | Exp 1: Skip ks=5,7,9 | 25 conv+30 unsolved | **HURTS 2 solved tasks (322@ks5, 299@ks9), helps 0 new** | **[-] REJECTED** |
-| 2026-04-26 | Exp 2: Best-of-N | 25 conv+30 unsolved | **No new solves on unsolved tasks** | **[~] NEUTRAL** — score opt only |
-| 2026-04-26 | Exp 3: Ridge reg | 4 victim tasks, 5 alphas | **0/4 pass arc-gen at any alpha** | **[-] REJECTED** |
-| 2026-04-26 | Exp 3: PCA/trunc-SVD | Task 129, thresh 0.5-0.99 | **0 pass, architecture mismatch** | **[-] REJECTED for lstsq** |
+| 2026-04-26 | Exp 1: Skip ks=5,7,9 | 25 conv+30 unsolved | **HURTS 2 solved tasks** | **[-] REJECTED** |
+| 2026-04-26 | Exp 2: Best-of-N | 25 conv+30 unsolved | **No new solves** | **[~] NEUTRAL** |
+| 2026-04-26 | Exp 3: Ridge reg | 4 victims × 5 alphas | **0/4 pass arc-gen** | **[-] REJECTED** |
+| 2026-04-26 | Exp 3: PCA/trunc-SVD (partial) | Task 129 | **0 pass** | **[-] REJECTED for lstsq** |
+| 2026-04-26 | **Exp 3: Full PCA/SVD** | **400 tasks** | **0 PCR solves, 0 regressions, code refactored** | **[-] REJECTED (code kept)** |
 
-### CRITICAL FINDING (2026-04-26)
+### CRITICAL FINDING (2026-04-26) — STRENGTHENED
 
-The "307→50 arc-gen survival gap" is **NOT primarily caused by lstsq overfitting**.
+The "307→50 arc-gen survival gap" is **NOT caused by lstsq overfitting**. Period.
 
-**Evidence:**
-1. Only 18 of 345 unsolved tasks pass train-fit at ks≤9. Of these, 17 use ks=5,7,9.
+**Evidence (strengthened with full Exp 3 data):**
+1. Only **10 of 345** unsolved same-shape tasks pass train-fit at any ks≤9.
 2. Ridge (L2) on 4 victim tasks × 5 alphas: **zero arc-gen passes**.
-3. PCA/truncated-SVD at thresholds 0.50-0.99: **zero arc-gen passes**.
-4. Inspecting victims reveals they require **global operations** (mode counting, flood fill) that NO local convolution can represent.
+3. PCA/truncated-SVD on 400 tasks with thresholds {0.999, 0.99, 0.95}: **zero arc-gen validates**.
+4. PCR improves arc-gen accuracy by 3-9% on 4 unsolved tasks — but 95.7% is the ceiling. 100% is required.
+5. For tasks where conv IS the right solver (25 tasks), lstsq already generalizes perfectly (100% arc-gen at p/n < 0.5).
 
-**Root cause reclassified:** Architecture mismatch, not regularization. The literature predictions (Nakkiran 2019) were correct in theory but inapplicable — the tasks that fail arc-gen fail because conv is the wrong solver type, not because of bad regularization.
+**Root cause:** Architecture mismatch. Tasks that fail arc-gen require operations (mode counting, flood fill, outline detection, conditional logic) that no local convolution can represent.
 
-**Impact on Phase 2:** Exps 1-5 are deprioritized. The fix must come from Phase 3 (new solver types) or new architectures. Best-of-N still useful for score optimization on existing solved tasks.
+**Impact:** Phase 2 regularization experiments are exhausted. Score improvement must come from:
+- Phase 1a: Opset 17 conversions (reduce cost on existing solved tasks)
+- Phase 3: New solver types (hash matchers, pattern detectors, LLM rescue)
+- Phase 4: ONNX optimization + scoring alignment
 
 ---
 
@@ -311,11 +228,11 @@ The "307→50 arc-gen survival gap" is **NOT primarily caused by lstsq overfitti
 
 ## Research Queue (Papers Read ✅ / To Read)
 
-1. ✅ **Nakkiran et al. 2019** (`1912.02292`) — Double descent, interpolation threshold peak at p≈n
-2. ✅ **Segert 2023** (`2311.11093`) — Truncated SVD/PCA > Ridge for low-rank covariance
-3. ✅ **Zhou & Ge 2023** (`2302.00257`) — L1 near-minimax for sparse signals, L2 fails
-4. ✅ **Liu et al. 2023** (`2302.01088`) — More rows help only with regularization
-5. ✅ **Liao & Gu 2024** (`2512.06104`) — CompressARC: regularization enables ARC generalization
+1. ✅ **Nakkiran et al. 2019** (`1912.02292`) — Double descent. Correct theory, inapplicable to our regime.
+2. ✅ **Segert 2023** (`2311.11093`) — PCA > Ridge. Tested: **0/400 PCR solves**.
+3. ✅ **Zhou & Ge 2023** (`2302.00257`) — L1 near-minimax for sparse signals. Untested.
+4. ✅ **Liu et al. 2023** (`2302.01088`) — More rows help only with regularization. Moot since regularization doesn't help.
+5. ✅ **Liao & Gu 2024** (`2512.06104`) — CompressARC. Different regime (MDL/KL vs conv lstsq).
 6. ✅ **Ali et al. 2019** — GD early stopping ≡ Ridge (therefore suboptimal here)
 7. [ ] **ARC Prize 2025 Technical Report** (`2601.10904`) — competition landscape, top approaches