paper
Provenance Tracking in AI Compilers through the Lens of Coalgebra
paperactiveprovisional
provenance-tracking-in-ai-compilers-through-the-lens-of-coalgebra-5a42b98d·1 events·first seen 7d agoAliases: Provenance Tracking in AI Compilers through the Lens of Coalgebra
Co-occurring entities
More like this (12)
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM AgentsProvenanceGuardProvenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data CurationAI-assisted theorem provingConcrete Problems in AI SafetyOperadic consistency: a label-free signal for compositional reasoning failures in LLMsExploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code InterpreterCharacterizing Cultural Localization in AI-Generated StoriesAgentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningGitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and MergeOperads for compositional reasoning in LLMsDetecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
Recent events (1)
Coalgebraic provenance tracking for AI compiler graph transformations
A preprint from arXiv introduces a lightweight provenance tracking approach for AI compilers that uses observational semantics and coalgebraic formalism rather than propagating identifiers through compiler passes. The method uses bisimulation to preserve provenance even when intermediate nodes are eliminated during normalization, lowering, and optimization. The authors implement the approach in a prototype compiler called COVAN, demonstrating stable provenance across compilation pipelines. Reliable provenance tracking is important for debugging, validating transformations, and attaching platform-specific postprocessing in production AI compiler stacks.