[{"data":1,"prerenderedAt":174},["ShallowReactive",2],{"run:lego-phase-g3-sh-progressive-30k":3,"run-findings:lego-phase-g3-sh-progressive-30k":144},{"run":4,"config":19,"metrics":53,"curve":59,"assets":143},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":18},"lego-phase-g3-sh-progressive-30k","Phase G.3 SH progressive 30k full validation","Run summary · P1 Phase G.3 30k validation","2026-05-25","splat","4c766b4",[12,13,14,15,16,17],"p1-g","phase-g","sh-progressive","lego-30k","brush-compat","premultiplied","partial",[20,23,26,29,32,35,38,41,44,47,50],{"key":21,"value":22},"dataset","\u002FUsers\u002Fotkrickey\u002Fdev\u002F3dgs-workspace\u002Fdatasets\u002Fnerf_synthetic\u002Flego",{"key":24,"value":25},"gt_convention","Premultiplied",{"key":27,"value":28},"iterations","30,000",{"key":30,"value":31},"seed","42",{"key":33,"value":34},"capacity","1,000,000 splats",{"key":36,"value":37},"sh_degree","3",{"key":39,"value":40},"loss","L1Ssim",{"key":42,"value":43},"lambda","0.200",{"key":45,"value":46},"ssim","window=7 sigma=1",{"key":48,"value":49},"backend.backward","Simd",{"key":51,"value":52},"backend.loss_path","Gpu",{"psnr":54,"wallclock":55,"wallclock_regress":56,"splats":57,"final_loss":58},36.384132385253906,"41m 7s",false,487741,"4.982112e-3",{"loss":60,"splats":125},{"iters":61,"values":93},[62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],1,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000,11000,12000,13000,14000,15000,16000,17000,18000,19000,20000,21000,22000,23000,24000,25000,26000,27000,28000,29000,30000,[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],0.5938448905944824,0.054110437631607056,0.013073215261101723,0.008165738545358181,0.0073289815336465836,0.006520536728203297,0.006182607263326645,0.005975950043648481,0.005788635928183794,0.005701151676476002,0.005524734500795603,0.005470297299325466,0.005362274125218391,0.005291810724884272,0.005307389423251152,0.005257892422378063,0.005209877155721188,0.005169305484741926,0.005178041756153107,0.0051729511469602585,0.005127977579832077,0.005038490518927574,0.0050510866567492485,0.005052028223872185,0.005044170189648867,0.004990758839994669,0.004984828643500805,0.004977301694452763,0.004931325558573008,0.004990684799849987,0.004982111509889364,{"iters":126,"values":127},[62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],[128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,57,57,57,57,57,57,57,57,57,57,57,57,57,57,57,57],5207,8235,193357,331673,404251,446118,472854,488961,497671,501771,502556,501438,499502,496068,491830,{"has_renders":56,"has_splat":56},[145],{"id":146,"title":147,"date":8,"status":148,"polarity":149,"category":150,"axes":151,"tags":152,"task_code":162,"related_runs":163,"delta_psnr":168,"delta_wallclock":169,"rank":170,"verdict":171,"impact_summary":172,"detail_path":173},"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",[62],[153,13,14,154,155,156,15,157,158,159,160,161],"p1-axis1","compute-reduction","pareto-front","lego-5k","stacked-config","implementation","unit-tests","bit-exact","smoke-artifact","P1 Phase G.3",[164,5,165,166,167],"lego-phase-g3-sh-progressive-5k","lego-phase-g1g3-stacked-15k","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]