Inference-Time Decision Calibration for Temporal Classification

• URL: http://arxiv.org/abs/2606.16034v1
• Date: Sun, 14 Jun 2026 22:02:48 GMT
• Title: Inference-Time Decision Calibration for Temporal Classification
• Abstract summary: Temporal classification errors can arise from how available evidence is converted into decisions.<n>This paper proposes a representation--calibration decomposition for temporal classification.
• Score: 0.607835026936425
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal classification errors are often treated as representation failures, but they can also arise from how available evidence is converted into decisions. This paper proposes a representation--calibration decomposition for temporal classification. We keep a trained native classifier frozen and separate two inference-time interventions: a conservative residual multi-scale branch that adds auxiliary logits to the native prediction, and a post-hoc branch-aware calibrator that recombines native and residual evidence at decision time. This design distinguishes missing temporal evidence from underused decision-level evidence without retraining the backbone. Across FI-2010, PTB-XL, UCI-HAR, MHEALTH, and HARTH, we find that gains are strongly regime-dependent. Residual multi-scale evidence is most useful in noisy or representation-limited settings, especially short-horizon FI-2010 and weaker recurrent backbones, while branch-aware calibration helps when native and auxiliary logits contain complementary evidence not fully exploited by the raw decision rule. Near-saturated settings show limited gains from either intervention. These results suggest that temporal classification should be understood not only as representation learning, but also as the problem of trusting, combining, and calibrating evidence from multiple views.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration [1.1803729553124735]
  Existing memory methods treat retrieved memories as independent evidence and combine them through voting or weighting.<n> memories written by different agents may inherit the same upstream source or shared bias, causing correlated evidence to be repeatedly counted and creating a false majority.<n>We propose textbfCorrelation-textbfAware textbfMemory textbfArbitration (CAMA) framework that jointly decouples retrieved memories and recovers missing independent evidence.
  arXiv  Detail & Related papers  (2026-08-20T06:50:23Z)
• Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders [47.8060666024071]
  We show that SASRec-style models exhibit highly localized last-item reliance.<n>We then find that residual addition sharply shifts the full-block representation toward same-position contributions.<n>Changing the residual strength induces a monotonic trade-off between structural mixing and last-item reliance.
  arXiv  Detail & Related papers  (2026-08-14T07:09:58Z)
• PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image Classification [49.52488260487956]
  In hyperspectral images, pixel representations are often ambiguous due to factors such as spectral similarity, mixed pixels, and local context interference.<n>We propose PNEC-Mamba, a prototype-guided positive-negative evidence calibration framework.<n>PNEC-Mamba achieves superior classification performance compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-08-03T08:45:13Z)
• Robustness Verification of Recurrent Neural Networks with Abstraction Refinement [0.0]
  We propose an abstraction-refinement framework for RNN verification that partitions such intervals to remove the dominant relaxation error.<n>Experiments on CIFAR10 and MNIST stroke benchmarks demonstrate consistent improvements in verification success and robustness-margin tightness over abstraction-only baselines.
  arXiv  Detail & Related papers  (2026-06-10T11:30:37Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition [87.22988227382329]
  Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict.<n>We propose Dual-Path Conflict Resolution (DCR), a unified framework that learns when to fuse and when to drop modalities.
  arXiv  Detail & Related papers  (2026-05-06T13:11:33Z)
• Affordance Agent Harness: Verification-Gated Skill Orchestration [45.231685718099264]
  Affordance grounding requires identifying where and how an agent should interact in open-world scenes.<n>We propose Affordance Agent Harness, a closed-loop runtime that unifies skills with an evidence store and cost control.
  arXiv  Detail & Related papers  (2026-05-01T13:45:16Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking [3.165340675929986]
  We develop a lightweight post-hoc reranker that combines a shrinkage-stabilized classwise term with a linear pairwise term driven by competition features on the shortlist.<n>Experiments on five benchmarks spanning image classification, species recognition, scene recognition, and rare disease diagnosis confirm that the decomposition explains where pairwise correction helps and where classwise correction alone suffices.
  arXiv  Detail & Related papers  (2026-04-02T00:34:12Z)
• The Alignment Bottleneck in Decomposition-Based Claim Verification [17.197804072440665]
  We introduce a new dataset of real-world complex claims featuring temporally bounded evidence and human-annotated sub-claim evidence spans.<n>We evaluate decomposition under two evidence alignment setups: Sub-claim Aligned Evidence (SAE) and Repeated Claim-level Evidence (SRE)<n>Our results reveal that decomposition brings significant performance improvement only when evidence is granular and strictly aligned.
  arXiv  Detail & Related papers  (2026-02-11T00:02:16Z)
• DoubleTake: Contrastive Reasoning for Faithful Decision-Making in Medical Imaging [0.0]
  We introduce a contrastive, document-aware reference selection framework that constructs compact evidence sets optimized for discrimination rather than similarity.<n>We propose Counterfactual-Contrastive Inference, a confidence-aware reasoning framework that performs structured pairwise visual comparisons and aggregates evidence using margin-based decision rules with faithful abstention.<n>On the MediConfusion benchmark, our approach achieves state-of-the-art performance, improving set-level accuracy by nearly 15% relative to prior methods while reducing confusion and improving individual accuracy.
  arXiv  Detail & Related papers  (2026-02-02T23:00:39Z)
• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• Action Quality Assessment with Temporal Parsing Transformer [84.1272079121699]
  Action Quality Assessment (AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. We propose a temporal parsing transformer to decompose the holistic feature into temporal part-level representations. Our proposed method outperforms prior work on three public AQA benchmarks by a considerable margin.
  arXiv  Detail & Related papers  (2022-07-19T13:29:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.