[{"data":1,"prerenderedAt":147},["ShallowReactive",2],{"run:lego-phase-f1-baseline-5k":3,"run-findings:lego-phase-f1-baseline-5k":92},{"run":4,"config":19,"metrics":53,"curve":59,"assets":91},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":18},"lego-phase-f1-baseline-5k","Phase F.1 baseline (use_simd_emit=false) re-take for A\u002FB","Run summary · P1 Phase F.1 A\u002FB baseline","2026-05-25","splat","b4fb0e6",[12,13,14,15,16,17],"p1-profile","axis-1","phase-f","ab-baseline","lego-5k","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","5,000",{"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},31.628820419311523,"1m 52s",false,82338,"1.448665e-2",{"loss":60,"splats":85},{"iters":61,"values":73},[62,63,64,65,66,67,68,69,70,71,72],1,500,1000,1500,2000,2500,3000,3500,4000,4500,5000,[74,75,76,77,78,79,80,81,82,83,84],0.5938448309898376,0.08621940016746521,0.055007148534059525,0.03255091607570648,0.019856154918670654,0.0172775499522686,0.016158297657966614,0.015520765446126461,0.015043020248413086,0.014779350720345974,0.014486652798950672,{"iters":86,"values":87},[62,63,64,65,66,67,68,69,70,71,72],[88,89,90,57,57,57,57,57,57,57,57],5207,842,11288,{"has_renders":56,"has_splat":56},[93,118],{"id":94,"title":95,"date":8,"status":96,"polarity":97,"category":98,"axes":99,"tags":100,"task_code":108,"related_runs":109,"delta_psnr":112,"delta_wallclock":113,"rank":114,"verdict":115,"impact_summary":116,"detail_path":117},"p1-axis1-phase-f1-emit-simd-falsified","Phase F.1 emit_pairs_simd + f16 forward gate flip — audit Tier 1 仮説 falsified、現規模で net regression \u002F no improvement","stable","negative","audit",[62],[101,14,102,103,104,105,106,107,16],"p1-axis1","emit-simd","f16-forward","tier-1","falsified","negative-finding","ab-test","P1 Phase F.1 \u002F F.2",[110,5,111],"lego-phase-f1-emit-simd-5k","lego-phase-f2-f16-fwd-5k","±0.13 dB (両者とも許容範囲、atomic\u002Ffp 順序由来)","+4.7% (emit_simd net regression) \u002F +2.5% (f16 fwd noise 圏内)","medium","audit-falsified-tier-1","audit (p1-axis1-metal-opt-audit) で Tier 1「即 actionable gate flip、-0.7-1.0% wallclock、zero risk」と分類した 2 候補を Lego 5k smoke A\u002FB で実証検証。\u003Cstrong>emit_pairs_simd は total wallclock +4.7% の net regression\u003C\u002Fstrong> (112.11s → 117.38s、~10 kernel 平均なので noise floor 小、real regression 確定)、ただし per-kernel emit_pairs 単体は +8.5% で baseline 2 sample 変動 (4.814 \u002F 5.129、6.5%) と近い hedge 必要。\u003Cstrong>f16 forward は ~+2.5% wallclock\u003C\u002Fstrong> (114.97s)、run-to-run variance 圏内で improvement \u002F regression いずれも明確に検出できず。\u003Cstrong>PSNR は両者で許容範囲\u003C\u002Fstrong> (emit_simd -0.132 dB、f16 +0.075 dB、atomic order \u002F fp 順序由来想定)。**audit の予測 calibration data**: Tier 1 SIMD-reduction 系の効果は theory より小さく overhead が打ち消し、Tier 2 別 mechanism (CPU-GPU sync 除去) は別途検証必要、Tier 2 同 family (backward TBDR) は falsification 拡大適用で skip 判断強化。卒論 narrative 価値: 「audit theoretical predictions vs empirical measurements」の方法論 paragraph を §5.4 negative findings 章 (chapter-5-4-negative-findings.md) に追加候補。","\u002Ffindings\u002Fp1-axis1-phase-f1-emit-simd-falsified\u002F",{"id":119,"title":120,"date":8,"status":96,"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)","positive","design",[62],[101,125,126,127,128,16,129,130,131,132,133,134],"phase-g","sh-progressive","compute-reduction","pareto-front","lego-30k","stacked-config","implementation","unit-tests","bit-exact","smoke-artifact","P1 Phase G.3",[137,138,139,5,140],"lego-phase-g3-sh-progressive-5k","lego-phase-g3-sh-progressive-30k","lego-phase-g1g3-stacked-15k","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",1782449788227]