WeSearch
Hub / Tags / Attribution
TAG · #ATTRIBUTION

Attribution coverage.

Every story in the WeSearch catalog tagged with #attribution, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

16 stories tagged with #attribution, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.

⌘ RSS feed for this tag →   or   search "Attribution"

RELATED TAGS
#ai3#ml2#data-attribution1#security1#cost-attribution1#observability1#multi-agent-systems1#failure-attribution1
PHYS.ORG

Attribution constraints reveal stronger future intensification of the upper‑level Hadley circulation

5 views ·
ARXIV CS.AI

StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems

LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks. However, these systems are highly sensitive to single-step execution errors…

5 views ·
#artificial intelligence#multi-agent systems#failure attribution
R/LOCALLLAMA

Vidai Community is now available: one Rust binary for cost attribution, guardrails and multi-provider routing on every LLM call

7 views ·
ARXIV CS.AI

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually govern…

7 views ·
#artificial intelligence#language models#machine learning
ARXIV CS.AI

BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems

Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose a coalition value function …

6 views ·
#artificial intelligence#machine learning
ARXIV CS.AI

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, t…

12 views ·
#artificial intelligence#machine learning#security
ARXIV CS.AI

The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Ga…

16 views ·
#ai#security#cryptography
ARXIV CS.AI

Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition

Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Bot…

13 views ·
#machine learning#artificial intelligence#transformers
USENIX

Duster: Tor Service Attribution Based on Flow Watermarking with Track Hiding [pdf]

10 views ·
#technology#privacy#security
DEV.TO (TOP)

Per-user cost attribution for your AI APP

You ship your AI feature. It works. A week later your OpenAI bill is $400 and you have no idea which...…

10 views ·
#ai#cost attribution#observability
R/MACHINELEARNING

l9gpu - open-source GPU observability with workload-level attribution [P]

17 views ·
INVESTING.COM — NEWS

TransUnion adds YouTube measurement to attribution solution

15 views ·
MOORACLE

FinOps for AI: per-commit cost attribution

Measure AI cost per feature, work item, or PR. The receipts are already on every commit — here's how to read them before GitHub Copilot's June 1 billing change.…

11 views ·
#finops#ai#software development
ARXIV CS.AI

On the Fragility of Data Attribution When Learning Is Distributed

Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods implicitly assume that attributi…

9 views ·
#machine learning#data attribution#security
ARXIV CS.AI

Interaction-Aware Influence Functions for Group Attribution

Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a …

13 views ·
#machine learning#artificial intelligence#influence functions
R/DEVOPS

Notes on monitoring Claude Code in production: OTel temporality, cost-as-estimate, cost attribution by team

13 views ·