provenance
12 Articles
How to Validate Knowledge Graph Embedding Predictions
A 2026 protocol for validating knowledge graph embedding predictions against original source spans, identity and time boundaries, then measuring supported-value precision and downstream answer support.
Sybil Attacks in Truth Discovery: A Stress Test
A 2026 research guide to Sybil attacks in truth discovery, comparing copied-source and controlled-identity threats, TDSSA evidence, factorial stress tests, and defensible failure thresholds.
LLM Context Compression Evidence Loss: An Acceptance Test
A 2026 guide to testing LLM context compression for evidence loss, with paired source bundles, exact-span scoring, citation-grounding data, and release rules for defensible answers.
Knowledge graph quality assessment for decisions
A 2026 guide to assessing whether a knowledge graph can support a named decision, with separate tests for correctness, coverage, freshness, provenance, uncertainty, and a reusable quality card.
How to Test Truth-Discovery Algorithms Before Choosing
A 2026 comparison of truth discovery algorithms using formal property tests, transparent baselines, empirical-Bayes conditions, benchmark design, and a reproducible acceptance protocol.
Fairness Tests for Truth-Discovery Aggregation
A 2026 evidence-based protocol for auditing truth-discovery aggregation across accuracy, disparity, coverage, uncertainty, dataset lineage, and downstream effects.
LLM Judge Groundedness Evaluation Calibration Protocol
A 2026 protocol for calibrating an LLM groundedness judge with controlled contradictions, paired judge-by-generator tests, confidence intervals, human review, and release gates.
Comparing Truth Discovery Methods Without Gold Labels
A 2026 protocol for evaluating truth discovery without ground truth, comparing synthetic stress tests, sparse adjudication, observation likelihood, stability, and uncertainty.
What Does a Fact-Verification Benchmark Test?
A 2026 guide to fact-verification benchmarks, covering system boundaries, evidence regimes, dataset scales, metric validity, leakage, and benchmark selection.
Bitemporal Data vs Temporal Knowledge Graphs: A Guide
A 2026 research comparison of valid time, transaction time, temporal link prediction, MRR, snapshot replay, benchmark design, and when to combine both models.
AI Agent Memory Update: When to Update or Abstain
A 2026 test framework for AI agent memory updates using two clocks, temporal fixtures, stale-answer rates, evidence reconstruction, conflict handling, and justified abstention.
Open World Assumption: Why Unknown Is Not False
A 2026 evidence guide to open-world negation, explicit negative knowledge, five epistemic states, local closure, negative sampling, and evaluation protocols.