NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
153 results for “keyword:"provenance"” in ICLR 2027. 47 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CERES: RECONCILING DURABLE EVIDENCE AND EVOLVING ACTIVE STATE FOR LONG-LIVED LLM AGENTS▼1.2k1.67
[PDF]Trust at the margin: Provenance-visibility effects and model-dependent risk localization in LLM knowledge conflicts▼4.3k2.00
[PDF]Gradient-Guided Radioactive Watermarking for Detecting Fine-Tuning on Teacher-Generated Data▼4.5k2.67
[PDF]From Traces to Guarded Programs: Evidence-Gated Compilation of Recurrent Agent Workflows▼1361.33
[PDF]CaseTCM: A Benchmark for Case-Preserving Cross-Source Retrieval in Traditional Chinese Medicine▼4.3k2.00
[PDF]Discourse Reconstructibility in Generative Language Models: Permutation-Invariant Bipartite Infilling, Representation Boundaries, and Non-Native Linguistic Invariance▼1361.33
[PDF]Fixed Rankings, Moving Leaders: A Relevance-Label and Source-Identity Audit of Scientific Retrieval Evaluation▼1361.33
[PDF]Every Guardrail Has a Floor: Deployment Limits of Action Guardrails from the Summary They Read▼4.3k2.00
[PDF]Provenance is not Universal: Discovering and Distilling Forensic Subspaces in Frozen Vision-Language Models▼5.8k2.33
Withdrawn or desk rejected (47)
[PDF]Same IoU, Different Decisions: Synthetic Mask Corruptions Mislead Classifiers Guided by SegmentationWithdrawn1.67
[PDF]ReAgg: Reliability-Aware Aggregation of Token Evidence for Machine-Generated Text DetectionWithdrawn1.67