[{"data":1,"prerenderedAt":147},["ShallowReactive",2],{"run:lego-phase-g1g3-stacked-15k":3,"run-findings:lego-phase-g1g3-stacked-15k":116},{"run":4,"config":21,"metrics":55,"curve":61,"assets":115},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":20},"lego-phase-g1g3-stacked-15k","Phase G.1+G.3 stacked variant (early stop + SH progressive)","Run summary · P1 Phase G.5 final Pareto integration","2026-05-25","splat","4c766b4",[12,13,14,15,16,17,18,19],"p1-g","phase-g","early-stop","sh-progressive","stacked","lego-15k","brush-compat","premultiplied","partial",[22,25,28,31,34,37,40,43,46,49,52],{"key":23,"value":24},"dataset","\u002FUsers\u002Fotkrickey\u002Fdev\u002F3dgs-workspace\u002Fdatasets\u002Fnerf_synthetic\u002Flego",{"key":26,"value":27},"gt_convention","Premultiplied",{"key":29,"value":30},"iterations","15,000",{"key":32,"value":33},"seed","42",{"key":35,"value":36},"capacity","1,000,000 splats",{"key":38,"value":39},"sh_degree","3",{"key":41,"value":42},"loss","L1Ssim",{"key":44,"value":45},"lambda","0.200",{"key":47,"value":48},"ssim","window=7 sigma=1",{"key":50,"value":51},"backend.backward","Simd",{"key":53,"value":54},"backend.loss_path","Gpu",{"psnr":56,"wallclock":57,"wallclock_regress":58,"splats":59,"final_loss":60},36.253822326660156,"16m 12s",false,427882,"5.346363e-3",{"loss":62,"splats":97},{"iters":63,"values":80},[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79],1,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000,11000,12000,13000,14000,15000,[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96],0.5938453078269958,0.0546429306268692,0.0136711485683918,0.008385207504034042,0.007437726482748985,0.006598528940230608,0.006201690062880516,0.00592968612909317,0.005788121372461319,0.005689150653779507,0.005582404788583517,0.005483000539243221,0.005459229461848736,0.005316551309078932,0.005381516646593809,0.005346362944692373,{"iters":98,"values":99},[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,59],5207,8277,184894,305997,363233,392791,410002,419734,424806,427184,427641,426973,426549,426492,426987,{"has_renders":58,"has_splat":58},[117],{"id":118,"title":119,"date":8,"status":120,"polarity":121,"category":122,"axes":123,"tags":124,"task_code":135,"related_runs":136,"delta_psnr":141,"delta_wallclock":142,"rank":143,"verdict":144,"impact_summary":145,"detail_path":146},"p1-axis1-phase-g3-sh-progressive","Phase G.3 SH-progressive — 5k smoke -14% は artifact、30k full は **quality improvement + 0.28 dB** に reframe、stacked + G.1 で **Pareto sweet spot** (Lego -61% wallclock + 0.15 dB)","stable","positive","design",[64],[125,13,15,126,127,128,129,130,131,132,133,134],"p1-axis1","compute-reduction","pareto-front","lego-5k","lego-30k","stacked-config","implementation","unit-tests","bit-exact","smoke-artifact","P1 Phase G.3",[137,138,5,139,140],"lego-phase-g3-sh-progressive-5k","lego-phase-g3-sh-progressive-30k","lego-phase-f1-baseline-5k","lego-brushcompat-opacdecay-30k","+0.15 dB stacked (vs Phase D)、+0.28 dB 30k single (vs Phase D)、-0.12 dB 5k smoke (許容)","**-61% stacked** (vs Phase D)、-1.9% 30k single、-13.9% 5k smoke (artifact)","high","pareto-sweet-spot-confirmed-chain-pending","Phase G compute reduction family の G.3 (SH-progressive growth) を実装 + bit-exact unit tests (11 件、cargo test 43 件 全 pass) + **3 layer の Lego 結果検証**。\u003Cstrong>(1) 5k smoke\u003C\u002Fstrong>: wallclock -13.9% \u002F splats -22% \u002F PSNR -0.12 dB、cascading splat reduction を観測。\u003Cstrong>(2) 30k full validation\u003C\u002Fstrong>: wallclock **-1.9%** (5k から大幅縮小)、splats **+30%** (5k から逆転)、PSNR **+0.28 dB** (quality improvement!)。5k smoke の cascading 効果は refine.stop_iter=1500 による artifact、30k では sh unlock 完了 (iter 3000) 後に refine が iter 15000 まで full SH で継続 → splats baseline より grow。\u003Cstrong>(3) G.1+G.3 stacked (max_steps=15000 + sh_progressive)\u003C\u002Fstrong>: Lego **16m13s \u002F 36.254 dB \u002F 428k splats** = Phase D 比 **-61% wallclock + 0.15 dB PSNR** で \u003Cstrong>Pareto sweet spot\u003C\u002Fstrong> 確定。\u003Cstrong>Key reframe\u003C\u002Fstrong>: G.3 は「speed win」ではなく「**quality improvement at no speed cost**」、stacked variant で G.1 speed と SH warmup quality gain を統合。\u003Cstrong>Implementation\u003C\u002Fstrong>: \u003Ccode>[trainer.sh_progressive]\u003C\u002Fcode> section (default disabled、全 backward compat)、\u003Ccode>CameraGpu\u003C\u002Fcode> struct を \u003Ccode>sh_degree\u003C\u002Fcode> (buffer layout) と \u003Ccode>active_sh_degree\u003C\u002Fcode> (per-iter eval) に分離。\u003Cstrong>Calibration data point\u003C\u002Fstrong>: Phase F 5 連続 falsification + G.3 5k smoke artifact = audit \u002F smoke overestimate 6 例目、「smoke は production scale を representative しない」が新教訓。8 scene chain validation pending。\u003Cstrong>卒論 narrative\u003C\u002Fstrong>: Phase F (kernel-level fail) → G.2 (architectural insight) → G.3 (algorithmic reframe: speed → quality + stacked Pareto) の 3 family 比較で「Apple Silicon native 最適化は \u003Cstrong>algorithmic compute reduction + early stop の組み合わせが Pareto-optimal\u003C\u002Fstrong>」という構造的 calibration。","\u002Ffindings\u002Fp1-axis1-phase-g3-sh-progressive\u002F",1782449788229]