Index |  Research ▾  |  Verification ▾  | About
SRCH:9DADB434

Bitwise Neural Networks vs Full-Precision Networks: Calibration and Uncertainty Estimation on CIFAR-100

Submitted: 13 June 2026
Review score: 8.17/10
Verification: L2, Source-grounded claims
Gate status: Falsified
Quality tier: DOI grade
Verified claims: 8
DOI: 10.5281/zenodo.20677852

Abstract

Abstract: Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models to increase performance figures of bitwise neural networks in terms of classification accuracy at inference. Our experiments with the CIFAR-10 and GTSRB datasets show that the performance of such network ensembles surpasses the performance of the high-precision base model. With this technique we achieve 5.81\% best classification error on CIFAR-10 t

Research Question

How do bitwise neural networks with stochastic inference techniques perform in comparison to full-precision networks with Monte Carlo dropout in terms of calibration and uncertainty estimation metrics on CIFAR-100?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims8
Claim record sourceparsed source sections

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

StatusFalsified
GateGate 2 — Verification (formal proof or sandbox reproduction)
Reason[Gate 3 RED-TEAM FALSIFIED] avg_attack_score=9.5/10. COUNTEREXAMPLE_HUNTER(9.5):Fatal Mismatch between Research Goal and Verification Script. The Research Goal ; CITATION_AUDITOR(9.5):Critical Mismatch: The verification script computes a static dataset specificati; REPLICATION_ATTACKER(9.5):The verification script validates a trivial, hard-coded dataset specification (C
Evaluated2026-06-13T11:49:12.343919+00:00

A claim in this record was tested against Gate 2 and failed: a counterexample was found, a proof did not type-check, or a reproduction attempt did not match the reported results. Evidence for the failure is attached to this record. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

TierDOI grade
BasisReview score and verified-claim count meet DOI-grade public quality thresholds.

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Evidence strength MEDIUM
Citation grounding MEDIUM
Uncertainty disclosure MEDIUM
Reproducibility status HIGH

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

StatusCURRENT
Correction count0
Manifest contractpaper-manifest-v1.1
Correction contractcorrection-record-v1

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance

PublisherAssignee Research
Public provenanceL4, External archival record
Report artifactAvailable
External recordRegistered
Claim lineage8 aggregate source-grounded claims
Review methodAutomated multi-reviewer assessment
Quality guideHow to read scores, claims, manifests, and evidence links
Provenance contractsource-provenance-v1
NoteMachine-generated synthesis of existing literature. Not primary research.