Paper Citation Record · LEDGER

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

As of 10 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 3 inbound Pith citation observations for arXiv:2506.13705.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.13705 v1

Coverage vector

measured 85 of 85 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:31:46.288448Z

measured 88 of 88 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:49:34.950522Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

85 of 85 outbound references displayed

verified exact0
verified fuzzy33
unresolved52
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 4f10c7f6-8c3d-4d1e-85a0-cd29a6254e72 · outbound

This paper cites Deep learning in human activity recognition with wearable sensors: A review on advances.Sensors, 22(4):1476, 2022.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Deep learning in human activity recognition with wearable sensors: A review on advances.Sensors, 22(4):1476, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.926768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ca9b5f-6cc5-4879-994c-c5f6ffb35057 · outbound

This paper cites Diverse intra-and inter-domain activity style fusion for cross-person generalization in activity recognition.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Diverse intra-and inter-domain activity style fusion for cross-person generalization in activity recognition

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.930649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c67754-10df-4c6c-be0b-bfe537d31819 · outbound

This paper cites Sensor alignment for multivariate time-series unsupervised domain adaptation.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Sensor alignment for multivariate time-series unsupervised domain adaptation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.933961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 687e86d8-33ab-4331-8f70-7165f6672b7a · outbound

This paper cites Conditional contrastive domain generalization for fault diagnosis.IEEE Transactions on Instrumentation and Measurement, 71:1–12, 2022.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Conditional contrastive domain generalization for fault diagnosis.IEEE Transactions on Instrumentation and Measurement, 71:1–12, 2022

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.937514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f2b10b-0e15-4f33-a011-05029fd4c8c0 · outbound

This paper cites Understanding electricity-theft behavior via multi-source data.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Understanding electricity-theft behavior via multi-source data

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.941002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61809e0b-1fbf-4272-914d-e0ae001efb60 · outbound

This paper cites Tactis: Transformer-attentional copulas for time series.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Tactis: Transformer-attentional copulas for time series

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.301899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62418048-9fdb-42a4-9129-a3d62808f8ab · outbound

This paper cites Tslanet: Rethinking transformers for time series representation learning.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Tslanet: Rethinking transformers for time series representation learning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.290762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 58d34a96-817f-4255-a9a9-567bbdaa2f91 · outbound

This paper cites Adacket: Adaptive convolutional kernel transform for multivariate time series classification.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Adacket: Adaptive convolutional kernel transform for multivariate time series classification

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.280411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7851a84a-da0f-4262-a41c-91dd4dd7134f · outbound

This paper cites TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.953844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c67d3941-077d-40a5-8d76-1b796b44d555 · outbound

This paper cites Recurrent neural networks for time series classification.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Recurrent neural networks for time series classification

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.270576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 72ddd7f7-b71a-4ca9-a6e2-c7c202cd7661 · outbound

This paper cites GPT-4 Technical Report.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning GPT-4 Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.961079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c85b1f-1ff7-4b85-b676-36b3df13da55 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Gemini: A Family of Highly Capable Multimodal Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.964303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0301e4e-8ac5-4423-ba6b-313be82a1ea2 · outbound

This paper cites Qwen Technical Report.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Qwen Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.967717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b371ac03-c6d2-4abe-8738-ec2f8f3a7ef1 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning LLaMA: Open and Efficient Foundation Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.971112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 693ab162-5cf4-4214-84fd-51037086d6b9 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Chain-of-thought prompting elicits reasoning in large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.974100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125d02c3-b2ec-48e2-8e5e-6a9c6b488119 · outbound

This paper cites Position: Empowering time series reasoning with multimodal llms.arXiv preprint arXiv:2502.01477, 2025.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Position: Empowering time series reasoning with multimodal llms.arXiv preprint arXiv:2502.01477, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.976997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b8406a-10f3-4365-b5d2-06ac82230552 · outbound

This paper cites A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.980014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba8bfe4-c359-463b-a6c0-f078166afefb · outbound

This paper cites Explainable multi-modal time series prediction with llm-in-the-loop.arXiv preprint arXiv:2503.01013, 2025.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Explainable multi-modal time series prediction with llm-in-the-loop.arXiv preprint arXiv:2503.01013, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.983591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfa2c6c9-712b-4c35-abb5-9012f2628e6a · outbound

This paper cites Language Models Still Struggle to Zero-shot Reason about Time Series.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Language Models Still Struggle to Zero-shot Reason about Time Series

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.986654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2deac758-c32c-4088-b920-27fde272e05c · outbound

This paper cites Gpt-4o, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Gpt-4o, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.254689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5a25663e-5bf1-4f77-9064-403564b9ed15 · outbound

This paper cites Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning.arXiv preprint arXiv:2412.03104, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning.arXiv preprint arXiv:2412.03104, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.993280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 312e5b5d-0846-4fe5-bfbc-101aa69ca9c6 · outbound

This paper cites Timecap: Learning to contextualize, augment, and predict time series events with large language model agents.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Timecap: Learning to contextualize, augment, and predict time series events with large language model agents

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.244733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 45a498d1-7723-4b12-83d8-f926c0535ba3 · outbound

This paper cites From news to forecast: Integrating event analysis in llm-based time series forecasting with reflection.Advances in Neural Information Processing Systems, 37:58118–58153, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning From news to forecast: Integrating event analysis in llm-based time series forecasting with reflection.Advances in Neural Information Processing Systems, 37:58118–58153, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:45.999008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec44d4e-8c68-4c3a-a7e8-fa016902dadd · outbound

This paper cites Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.001781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6700148f-a925-4bad-8def-4db186fffa1c · outbound

This paper cites Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.004562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e2f8ce-87ed-4fd0-b820-d95b77d0521b · outbound

This paper cites Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.007674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caeb3e68-5a14-4c18-b675-4131a7a4b376 · outbound

This paper cites Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.012164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2293c1b-0522-4d3f-82eb-5b89f94de063 · outbound

This paper cites Gpt4mts: Prompt-based large language model for multimodal time-series forecasting.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Gpt4mts: Prompt-based large language model for multimodal time-series forecasting

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.228488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16134222-26a6-447e-95d9-7bcbb68753d0 · outbound

This paper cites MIT press, 2018.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning MIT press, 2018

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.018071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a629ef-c176-4d6b-96ea-ac988c2c04de · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.020895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45e361f-a7c0-4596-a48f-43f8ed919595 · outbound

This paper cites Time-LLM: Time Series Forecasting by Reprogramming Large Language Models.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.023863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50a5f697-b1e9-4838-b249-644966157ff3 · outbound

This paper cites Autotimes: Au- toregressive time series forecasters via large language models.Advances in Neural Information Processing Systems, 37:122154–122184, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Autotimes: Au- toregressive time series forecasters via large language models.Advances in Neural Information Processing Systems, 37:122154–122184, 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.027174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab47558a-20fb-48e6-a032-b796a2c053a8 · outbound

This paper cites Calf: Aligning llms for time series forecasting via cross-modal fine-tuning.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Calf: Aligning llms for time series forecasting via cross-modal fine-tuning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.029877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a73c42-11de-4cfc-ac12-c192f33cc5e8 · outbound

This paper cites Test: Text prototype aligned embedding to activate llm’s ability for time series.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Test: Text prototype aligned embedding to activate llm’s ability for time series

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.194169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf1c8c4e-b663-4400-b92a-484a7a862a51 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.135435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c56553e6-2a87-4714-a355-509808a1501f · outbound

This paper cites How can time series analysis benefit from multiple modalities? a survey and outlook.arXiv preprint arXiv:2503.11835, 2025.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning How can time series analysis benefit from multiple modalities? a survey and outlook.arXiv preprint arXiv:2503.11835, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.139839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09c38aa-3a62-4144-bec9-23cd83814423 · outbound

This paper cites Timecma: Towards llm-empowered multivariate time series forecasting via cross-modality alignment.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Timecma: Towards llm-empowered multivariate time series forecasting via cross-modality alignment

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.142662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28707692-27d3-4054-811b-5780e3fd3e6b · outbound

This paper cites MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.145417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae24406-5b7c-4eff-9718-794020b7cbcf · outbound

This paper cites Multi-modal deep learning for credit rating prediction using text and numerical data streams.Applied Soft Computing, page 112771, 2025.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Multi-modal deep learning for credit rating prediction using text and numerical data streams.Applied Soft Computing, page 112771, 2025

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.171021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 404f18de-ca3b-42bb-a477-7b76d8b928cf · outbound

This paper cites Terra: A multimodal spatio-temporal dataset spanning the earth.Advances in Neural Information Processing Systems, 37:66329– 66356, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Terra: A multimodal spatio-temporal dataset spanning the earth.Advances in Neural Information Processing Systems, 37:66329– 66356, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.151732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8eff1f0-aae2-404c-bc94-930f93cce744 · outbound

This paper cites Bjtt: A large-scale multimodal dataset for traffic prediction.IEEE Transactions on Intelligent Transportation Systems, 2024.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Bjtt: A large-scale multimodal dataset for traffic prediction.IEEE Transactions on Intelligent Transportation Systems, 2024

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.154577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1c59c83e-00f8-4678-8bca-6d7fa87e88ca · outbound

This paper cites Event traffic forecasting with sparse multimodal data.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Event traffic forecasting with sparse multimodal data

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.144835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3cd1358e-60cc-4a45-8ad8-f851e5095028 · outbound

This paper cites Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.160500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d5146f1-d429-412c-9cbf-224a8fb9abf9 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Fine-Tuning Language Models from Human Preferences

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.164151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e95f30d-a8d5-45a2-acaf-82686b33bdb3 · outbound

This paper cites Learning to summarize with human feedback.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Learning to summarize with human feedback

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.167249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fed3d62a-89f5-4f56-a9ad-559da44a862e · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.170091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d4b5060-708a-4b59-b827-ce0b1306f120 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Direct preference optimization: Your language model is secretly a reward model

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.123357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd806d46-bec8-4fa6-893e-bc01d274144d · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.176717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee1c1a36-35fa-4cae-877f-2290a92ff7c3 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.179757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6311a86-694e-41ac-8ce1-4e63ab5f5b3f · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.184098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f785702e-4f3b-410f-be9b-d44a82b06407 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.187814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35f0c74-fb97-4142-b4f6-a66dd7652d16 · outbound

This paper cites iTransformer: Inverted Transformers Are Effective for Time Series Forecasting.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.191093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a91a9e5d-b3c9-4d1f-ac58-1dd61baa1bfd · outbound

This paper cites A Time Series is Worth 64 Words: Long-term Forecasting with Transformers.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.194378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b34f629-360a-4764-bd66-60f447dc7640 · outbound

This paper cites Beyond numbers: A survey of time series analysis in the era of multimodal llms.Authorea Preprints, 2025.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Beyond numbers: A survey of time series analysis in the era of multimodal llms.Authorea Preprints, 2025

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.113581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ac1573a8-354a-481c-a473-11eb203feb0a · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.200348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa0b0042-2dd5-4228-bda1-693a08226128 · outbound

This paper cites Autoformer: Decomposition trans- formers with auto-correlation for long-term series forecasting.Advances in neural information processing systems, 34:22419–22430, 2021.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Autoformer: Decomposition trans- formers with auto-correlation for long-term series forecasting.Advances in neural information processing systems, 34:22419–22430, 2021

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.203029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f4b35a-2f59-4c23-add1-92c4cf544e40 · outbound

This paper cites Informer: Beyond efficient transformer for long sequence time-series forecasting.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Informer: Beyond efficient transformer for long sequence time-series forecasting

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.205888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f13a7a1-63c2-41ce-9bfc-25308ee3fd52 · outbound

This paper cites Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.208650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122ac7f3-6349-47a6-9593-acf5541663c0 · outbound

This paper cites Are transformers effective for time series forecasting? InProceedings of the AAAI conference on artificial intelligence, volume 37, pages 11121–11128, 2023.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Are transformers effective for time series forecasting? InProceedings of the AAAI conference on artificial intelligence, volume 37, pages 11121–11128, 2023

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.211469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4abdc964-d06b-456f-b8c9-1529338f7768 · outbound

This paper cites Qwen2.5-VL Technical Report.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Qwen2.5-VL Technical Report

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.214321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58446f4d-ffde-428a-bc6f-8f5e86db65cd · outbound

This paper cites The x -axis should reflect forward motion , while the y and z axes can show lateral and vertical changes.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning The x -axis should reflect forward motion , while the y and z axes can show lateral and vertical changes

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.072162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cca7a7b0-ad0f-47d5-a24b-cceb3314262c · outbound

This paper cites The fluctuations would be larger and more pronounced in z -axis data due to the changes in vertical motion.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning The fluctuations would be larger and more pronounced in z -axis data due to the changes in vertical motion

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.062391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c4f9259-bf83-4d56-a6a7-3f7c40e87371 · outbound

This paper cites an unresolved cited work.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:31:47.052883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 121f68ac-24eb-413e-ac7e-dcd6c849ed3b · outbound

This paper cites LAYING” based on vague cues like “relatively small movements.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning LAYING” based on vague cues like “relatively small movements

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.043735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eb4308c0-a826-456b-8c29-e3dfb501e762 · outbound

This paper cites This is typical in neuropathy due to reinnervation and the presence of motor units with abnormal recruitment patterns.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning This is typical in neuropathy due to reinnervation and the presence of motor units with abnormal recruitment patterns

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.034673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3cbb8b6-bf98-41b5-8b2c-6200ff8b7f56 · outbound

This paper cites The polyphasic nature of the waveform is indicative of reinnervation, where motor units are recruited in a different manner than in a healthy state.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning The polyphasic nature of the waveform is indicative of reinnervation, where motor units are recruited in a different manner than in a healthy state

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.025649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 02bc1eba-dae0-41be-8ebf-ad357ac833f9 · outbound

This paper cites </think> <class>Neuropathy</class> < t h i n k>1.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning </think> <class>Neuropathy</class> < t h i n k>1

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.015106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4a77a33f-a584-431b-8660-39bed8b0fbf1 · outbound

This paper cites The waveform is polyphasic, meaning it has multiple peaks and troughs within the waveform.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning The waveform is polyphasic, meaning it has multiple peaks and troughs within the waveform

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:47.006113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation daaa1a47-92ee-4440-b316-31f635381694 · outbound

This paper cites an unresolved cited work.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:31:46.997223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 716885c3-69da-4112-be60-cdcbf8affcc8 · outbound

This paper cites - Myopathy: Typically shows small amplitude and short duration , indicating a loss or dysfunction of muscle fibers.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning - Myopathy: Typically shows small amplitude and short duration , indicating a loss or dysfunction of muscle fibers

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.988781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 84353257-71be-4119-b91c-8040c48a3302 · outbound

This paper cites </think> <class>Neuropathy</class> <think > 1.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning </think> <class>Neuropathy</class> <think > 1

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.979545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c11fcad5-3f5f-47fa-83cd-11834e2f513d · outbound

This paper cites The waveform morphology is consistent with normal recruitment and morphology of motor unit potentials.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning The waveform morphology is consistent with normal recruitment and morphology of motor unit potentials

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.969212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 64cac3d0-82d8-42e8-bf0a-400a9061fa75 · outbound

This paper cites WALKING_UPSTAIRS.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning WALKING_UPSTAIRS

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.958756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 63126304-7b9f-476f-8bd2-3101d8b60097 · outbound

This paper cites walking up stairs.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning walking up stairs

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.950209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 001ac3a2-b186-40ab-9084-4036fee0afde · outbound

This paper cites atrial fibrillation.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning atrial fibrillation

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.941560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 567ba4e2-37cd-43a8-a9ed-281aaba095cc · outbound

This paper cites IR Negative.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning IR Negative

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.932731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation def5ac96-f89b-4b70-8f0f-5115fa5ffe31 · outbound

This paper cites NOWHALE,.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning NOWHALE,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.924505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8cc0cf5c-4736-48ce-be0a-dd07eda432b2 · outbound

This paper cites an unresolved cited work.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:31:46.914931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f6953110-8782-44d3-9f6b-48973cd514ac · outbound

This paper cites an unresolved cited work.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:31:46.906463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d2d9e40-db75-4500-a328-6a0288c7f5a3 · outbound

This paper cites an unresolved cited work.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:31:46.897458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7fdeec42-ec5d-4a07-a42b-c1526a119eea · outbound

This paper cites be careful.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning be careful

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.888044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c269e863-46f7-4fad-af19-4258a41186e6 · outbound

This paper cites Since the sampling rate is 2kHz, any frequency components within this range should be detectable.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Since the sampling rate is 2kHz, any frequency components within this range should be detectable

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.879104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8161b69-2cf3-4718-9144-5b3a612b525b · outbound

This paper cites Given the 2-second duration of the waveform, any call should be visible if it exists.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning Given the 2-second duration of the waveform, any call should be visible if it exists

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.869128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b253a405-04a3-4997-98da-4a19f821ff82 · outbound

This paper cites This would likely appear as a consistent pattern or peak within the correct frequency range over the duration of the call.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning This would likely appear as a consistent pattern or peak within the correct frequency range over the duration of the call

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.858858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ef0e01c-dbb7-41ec-8e36-ae4ca22dfcb5 · outbound

This paper cites ] Generated Reasoning Sample (HAR) [.

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning ] Generated Reasoning Sample (HAR) [

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:31:46.847015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 4eeba1b1-c73d-4706-be40-4fbb76556647 · inbound

A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting cites this paper.

A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-24T02:23:45.925864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 010ad09b-d88a-4ded-964b-308255366058 · inbound

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models cites this paper.

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Reference 140

Resolution: unresolved; no resolver link, observed 2026-08-04T16:49:34.950522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c2e6fa-b90a-4bf2-b6e8-f00c7466416a · inbound

Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models cites this paper.

Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T11:39:25.286370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.