@prefix this: . @prefix sub: . @prefix np: . @prefix dct: . @prefix xsd: . @prefix rdfs: . @prefix prov: . @prefix npx: . sub:Head { this: np:hasAssertion sub:assertion; np:hasProvenance sub:provenance; np:hasPublicationInfo sub:pubinfo; a np:Nanopublication . } sub:assertion { dct:title "A Time Series Multitask Framework Integrating a Large Language Model, Pre-Trained Time Series Model, and Knowledge Graph"; , , ; , , , , , , , , , , , , , , , , , , , , , , , , , , , ; a prov:Entity . a ; rdfs:label "ARIMA" . a ; rdfs:label "Anomaly Transformer" . a ; rdfs:label "Auto-TTE" . a ; rdfs:label "AutoTimes" . a ; rdfs:label "Autoformer" . a ; rdfs:label "Chat-GPT" . a ; rdfs:label "ChatGLM" . a ; rdfs:label "DLinear" . a ; rdfs:label "ETSformer" . a ; rdfs:label "Exponential Smoothing" . dct:subject ; a ; rdfs:comment "This module deeply integrates natural language prompt embeddings (derived from the LLM) with time series data. It aligns pooled text features with temporal segments and uses multi-scale convolutions to combine them effectively. This process aims to create a unified representation by merging semantic knowledge from the LLM with temporal patterns, thereby enhancing the model's ability to learn complex patterns for time series tasks."; rdfs:label "Fusion-Aware Temporal Module"; . a ; rdfs:label "GPT" . a ; rdfs:label "GRU" . a ; rdfs:label "GraphRAG" . a ; rdfs:label "Informer" . dct:subject ; a ; rdfs:comment "This module leverages a Knowledge Graph (KG) to enrich user-provided prompts with task-relevant semantics and descriptive insights for time series analysis. By incorporating retrieved knowledge into the prompt, it enhances the LLM's input at the inference stage, allowing the LLM to access external knowledge to improve its performance on time series tasks."; rdfs:label "Knowledge-Driven Temporal Prompt"; . a ; rdfs:label "LLM4TS" . a ; rdfs:label "LLMTime" . a ; rdfs:label "LLaMA" . a ; rdfs:label "LPTM" . a ; rdfs:label "LSTM" . dct:subject ; a ; rdfs:comment "LTM is a novel multi-task framework that integrates time series models, LLMs, and KGs for tasks like forecasting, imputation, and anomaly detection. It achieves a deep fusion of temporal and semantic features by combining KG-enhanced prompts with LLM processing and feature fusion modules, representing knowledge from both LLMs and KGs in a unified manner for time series analysis."; rdfs:label "LTM"; . a ; rdfs:label "RNN" . a ; rdfs:label "SDformer" . a ; rdfs:label "State-Space Models" . a ; rdfs:label "TIME-FFM" . a ; rdfs:label "TTM" . a ; rdfs:label "Temporal Fusion Transformer" . a ; rdfs:label "Time-LLM" . a ; rdfs:label "Timer" . a ; rdfs:label "TimesNet" . } sub:provenance { sub:assertion prov:wasAttributedTo ; prov:wasDerivedFrom . } sub:pubinfo { this: dct:created "2026-02-26T15:50:08.769Z"^^xsd:dateTime; dct:creator ; npx:hasNanopubType ; rdfs:label "LLM-KG assessment for paper 10.48550/arXiv.2503.07682" . sub:sig npx:hasAlgorithm "RSA"; npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB"; npx:hasSignature "JKPy8S63KDFUl92+KjwgclIoG8ep+Mg0sGqa/p/ZOWnFwFDdNNXwzMAgsJZ22NZR1JdazRGDhUgp7MqnJlzGzm9+LGw7s+K4G+V9Ggp65NZTSdUhcVu6Z9PT9QRkV7ajpbYmWNRVLTdkmAvbKM5i9T/FHU72f7T1qiBqRvZbB444asW4C/QBrADc41cEm2PLszWC6RtyjyhCCerdmxowIn+5pyV6m3LJ83XpTMbaJoGYXYGo5naIhyk8Y9qBFPQ7Qoi+QHMxAXipc4DfelTC5FLgYdYn6SOO+HQt7DU1oqv9/wakPKgO95EYDi+t3m0PXIql9sKpjg0N69GNmUPJRg=="; npx:hasSignatureTarget this:; npx:signedBy . }