PUMA Vault
Search
Buscar
Modo oscuro
Modo claro
Explorador
Etiqueta: result-note
69 artículos con esta etiqueta.
15 jun 2026
RES — A post-implementation mypy --strict audit surfaced 104 pre-existing type…
result-note
puma
reference
15 jun 2026
RES — The 'sunk CO2 cost' finding: an unparseable model family…
result-note
puma
reference
sweep
15 jun 2026
RES — Sprint 6 (v2.0.0) established the canonical baseline: 200 triage…
result-note
puma
reference
triage
estimation
f1-macro
baseline
15 jun 2026
RES — Sprint 7 (v2.4.0) ran the full Phase B sweep and documented 7 findings…
result-note
puma
reference
triage
estimation
sweep
sprint
15 jun 2026
RES — Sprint 8 produced the canonical H2 test: Wilcoxon does NOT reject H0_2…
result-note
puma
reference
wilcoxon
sprint
15 jun 2026
RES — Methodological finding F1: the reference baseline F1=0.5867 corresponds to…
result-note
puma
reference
triage
contextual-anchoring
zero-shot
baseline
15 jun 2026
RES — Nine candidate open-weights models were selected (1B-12B across four families)
result-note
puma
methodology
open-weights
15 jun 2026
RES — The canonical triage baseline (3B + contextual-anchoring, N=200) achieves…
result-note
puma
methodology
triage
f1-macro
reproducibility
contextual-anchoring
15 jun 2026
RES — Per-class triage: Critical is best discriminated (F1=0.816) via explicit…
result-note
puma
methodology
triage
15 jun 2026
RES — The triage confusion matrix shows errors confined to adjacent severities…
result-note
puma
methodology
triage
calibration
15 jun 2026
RES — In the triage sweep (N=100) the largest 12B model leads on F1-macro…
result-note
puma
methodology
triage
f1-macro
sweep
15 jun 2026
RES — Model quality is non-monotonic with size within families
result-note
puma
methodology
triage
f1-macro
15 jun 2026
RES — A keyword-heuristic baseline originally planned for triage was…
result-note
puma
methodology
triage
baseline
15 jun 2026
RES — The best estimation configuration achieves MAE=1.86 SP (7B model,…
result-note
puma
methodology
estimation
mae
contextual-anchoring
zero-shot
15 jun 2026
RES — H1 is REJECTED: the canonical triage config beats the majority-class…
result-note
puma
methodology
triage
wilcoxon
baseline
15 jun 2026
RES — H2 is NOT REJECTED: the best estimation config (7B, MAE=1.86 SP) does not…
result-note
puma
methodology
estimation
mae
wilcoxon
baseline
15 jun 2026
RES — The full sweep covers 27 conditions (9 models x 3 scenarios x 100 = 2,700…
result-note
puma
methodology
sweep
15 jun 2026
RES — A single non-parseable model family (parse-failure rate >= 0.98) consumed…
result-note
puma
methodology
sweep
15 jun 2026
RES — Small models lead in raw efficiency (quality per gram CO2) for triage and…
result-note
puma
methodology
triage
estimation
15 jun 2026
RES — Estimated against frontier commercial models, the local 3B model's…
result-note
puma
methodology
reproducibility
15 jun 2026
RES — Latency on the reference laptop profile is consistently under 3 s (P95)…
result-note
puma
methodology
latency
15 jun 2026
RES — All five MVP acceptance criteria are met comfortably (F1-macro, MAE,…
result-note
puma
methodology
f1-macro
mae
reproducibility
hypothesis
15 jun 2026
RES — Three consecutive warm-state runs of the canonical config produce…
result-note
puma
methodology
f1-macro
mae
reproducibility
latency
15 jun 2026
RES — Qualitative triage error analysis codes four recurring types
result-note
puma
methodology
triage
dataset
15 jun 2026
RES — Contextual-anchoring is identified as an effective prompt-engineering…
result-note
puma
methodology
contextual-anchoring
release
15 jun 2026
RES — Native integration of sustainability as a first-class experimental…
result-note
puma
methodology
sustainability
carbon
15 jun 2026
RES — The empirical answer to the research question is asymmetric
result-note
puma
methodology
triage
estimation
mae
15 jun 2026
RES — Bit-exact warm-state reproducibility for non-trivial local-LLM tasks is a…
result-note
puma
methodology
reproducibility
local-llm
15 jun 2026
RES — Reproducible evaluation on consumer laptop hardware requires attention to…
result-note
puma
methodology
15 jun 2026
RES — Several methodological findings during validation (script renaming,…
result-note
puma
methodology
latency
technical-debt
15 jun 2026
RES — A cold-vs-warm drift of up to 0.006 F1-macro points was observed between…
result-note
puma
methodology
f1-macro
15 jun 2026
RES — Reproducibility is achieved by design with seed=42 and temperature=0.0…
result-note
puma
engine
reproducibility
metrics
15 jun 2026
RES — The canonical triage baseline is F1-macro = 0.5867 (qwen2.5:3b,…
result-note
puma
engine
triage
f1-macro
contextual-anchoring
zero-shot
15 jun 2026
RES — The canonical estimation baseline is MAE = 5.7150 SP (qwen2.5:3b,…
result-note
puma
engine
estimation
mae
zero-shot
baseline
15 jun 2026
RES — The best reproducible estimation configuration observed is qwen2.5:7b at…
result-note
puma
engine
estimation
story-points
mae
sweep
15 jun 2026
RES — A three-seed validation {42,123,456} of the triage baseline produced…
result-note
puma
engine
triage
f1-macro
baseline
metrics
15 jun 2026
RES — No single model wins across all PMO tasks
result-note
puma
engine
triage
estimation
mae
15 jun 2026
RES — A parser x hardware incompatibility can waste more compute than the useful…
result-note
puma
engine
sweep
15 jun 2026
RES — On the reference gpu-entry host a 200-instance canonical run costs a…
result-note
puma
engine
triage
estimation
baseline
15 jun 2026
RES — Cross-architecture (x86_64 vs arm64 Apple Silicon) bit-exactness of F1/MAE…
result-note
puma
engine
mae
architecture
15 jun 2026
RES — Gender-prefix robustness testing on triage found qwen2.5:3b shifts…
result-note
puma
engine
triage
15 jun 2026
RES — The most consequential cost-effectiveness finding: qwen2.5:1.5b
result-note
puma
engine
triage
estimation
carbon
15 jun 2026
RES — gemma3:12b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — gemma3:12b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — gemma3:12b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — gemma3:1b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — gemma3:1b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — gemma3:1b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — gemma3:4b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — gemma3:4b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — gemma3:4b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — gemma4:e2b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — gemma4:e2b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — gemma4:e2b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — llama3.1:8b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — llama3.1:8b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — llama3.1:8b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — mistral:7b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — mistral:7b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — mistral:7b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — qwen2.5:1.5b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — qwen2.5:1.5b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — qwen2.5:1.5b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — qwen2.5:3b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — qwen2.5:3b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — qwen2.5:3b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine
15 jun 2026
RES — qwen2.5:7b · estimation (Phase-B cell)
result-note
puma
benchmark
estimation
engine
15 jun 2026
RES — qwen2.5:7b · prioritization (Phase-B cell)
result-note
puma
benchmark
prioritization
engine
15 jun 2026
RES — qwen2.5:7b · triage (Phase-B cell)
result-note
puma
benchmark
triage
engine