docs: Update model card with official 150k Decision Index 0.2.1 ground truth (30.65 raw, 9.58 skill)

weights: release P2+P3 Grand Champion Soup (uncontaminated 1.21 Balanced Raw, 63.1 JevBench, 55.8% cb_v2)

weights: update decision metadata with soup temperature 0.3236

docs: update model card with official Decision Index results, 2k-case benchmarks, and calibrated temperature

docs: update benchmark presentation (JevBench 68.11, Classifier-Bench 57.1%, honest OOD breakdown)

weights: update to grand model soup (Skill 44.21, JevBench 68.11, ECE 0.1690)

docs: refresh model card with SOTA 44.21 Decision Index and 68.11 JevBench composite

weights: update to uncontaminated champion model soup (43.50 Decision Index SOTA, 57.82 cb-v2)

update decision_meta.json for clean uncontaminated release

docs: refresh model card with clean uncontaminated Decision Index SOTA results and modern quickstarts

card: present as v0, no internal versioning

v3 weights: noulhalved-1M + 10% procedural (cbv2 60.5/60.0, b77 47.8)

docs: consolidate v0 benchmark results

correct Tasksource rows to heterogeneous-split probes

plain-language card: public-only example, sub-200M table

v0: 512k natural typed sq_o (dev_selected step 4000) + card

initial commit