Motif 3: Technical Report | Paper Citation Record

Observation 96f7824b-af72-45ca-94c4-b066ab27a3ba · outbound

This paper cites Open-swe-traces: Advancing dual-mode multilingual distillation for software engineering agents.arXiv preprint arXiv:2606.16038, 2026.

Motif 3: Technical Report Open-swe-traces: Advancing dual-mode multilingual distillation for software engineering agents.arXiv preprint arXiv:2606.16038, 2026

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.825707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352dba50-6749-42e0-9915-6d0e5411b031 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Motif 3: Technical Report GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.831671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841138b4-2724-4e69-8baf-5a5130e03212 · outbound

This paper cites Artificial analysis long context reasoning benchmark (AA-LCR).

Motif 3: Technical Report Artificial analysis long context reasoning benchmark (AA-LCR)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.727269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 40aa0b26-a862-4a1c-a28d-1b757effdcea · outbound

This paper cites GDPval-AA v2 leaderboard.

Motif 3: Technical Report GDPval-AA v2 leaderboard

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.706703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b6625f1d-cf36-4563-9c2b-fc35cddbc030 · outbound

This paper cites ITBench-AA benchmark leaderboard.

Motif 3: Technical Report ITBench-AA benchmark leaderboard

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.686022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fa898f5c-a7e0-46f9-9761-2f37619f2734 · outbound

This paper cites Online benchmark and leaderboard, 2026.

Motif 3: Technical Report Online benchmark and leaderboard, 2026

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.669642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5185f0e5-841c-4aa7-b863-672c442b734a · outbound

This paper cites Program Synthesis with Large Language Models.

Motif 3: Technical Report Program Synthesis with Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.857957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0ef21b-96ac-4424-ab24-8974ed0a099e · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

Motif 3: Technical Report $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.863007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50f4243-4533-4305-aadb-db1254c99409 · outbound

This paper cites PIQA: Reasoning about physical commonsense in natural language.Proceedings of the AAAI Conference on Artificial Intelligence, 2020.

Motif 3: Technical Report PIQA: Reasoning about physical commonsense in natural language.Proceedings of the AAAI Conference on Artificial Intelligence, 2020

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.651150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 199e88d6-ca7d-46ff-9779-2cd69ff64e3f · outbound

This paper cites Striped Attention: Faster Ring Attention for Causal Transformers.

Motif 3: Technical Report Striped Attention: Faster Ring Attention for Causal Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.873268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58dd115d-3f9b-4094-9d29-0a3d1c046c96 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Motif 3: Technical Report Evaluating Large Language Models Trained on Code

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.879247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00acdfe-bf4a-4e3e-a746-186b50672570 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Motif 3: Technical Report Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.884723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d348bc73-30ba-441d-9d03-714343bc4085 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Motif 3: Technical Report Training Verifiers to Solve Math Word Problems

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.890228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0858f7e-9ac6-49bd-b227-d4ba0c732763 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Motif 3: Technical Report DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.896042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f21ccd-3edc-476e-8f72-bf4d16546030 · outbound

This paper cites DeepSeek-V3 Technical Report.

Motif 3: Technical Report DeepSeek-V3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.900991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03229335-269f-4c32-8f16-8163414fc04a · outbound

This paper cites DeepEP: Hybrid expert-parallel communication.

Motif 3: Technical Report DeepEP: Hybrid expert-parallel communication

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.631570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8124b7f4-17dc-49ef-802c-09147d7e1253 · outbound

This paper cites DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, June 2026.

Motif 3: Technical Report DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, June 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.911684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cea9e0b-9a49-4487-83cd-920769eed99c · outbound

This paper cites Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs.

Motif 3: Technical Report Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.916832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381efd72-9d36-46f9-82e4-76da54536f5d · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Motif 3: Technical Report GLM-5: from Vibe Coding to Agentic Engineering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.921673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3588dac7-b590-4ab2-abd8-4a4a8e694ebb · outbound

This paper cites Measuring massive multitask language understanding.International Conference on Learning Representations, 2021.

Motif 3: Technical Report Measuring massive multitask language understanding.International Conference on Learning Representations, 2021

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.605477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1858c407-b6bc-47fe-b373-97f9a0ca6b0e · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.NeurIPS Datasets and Benchmarks, 2021.

Motif 3: Technical Report Measuring mathematical problem solving with the MATH dataset.NeurIPS Datasets and Benchmarks, 2021

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.931747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 233b03fc-430f-4ebc-8bd8-207738f4ba10 · outbound

This paper cites Liger Kernel: Efficient Triton Kernels for LLM Training.

Motif 3: Technical Report Liger Kernel: Efficient Triton Kernels for LLM Training

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.937202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38b03e6b-efa1-419c-b898-0a2ac5fecc36 · outbound

This paper cites Aa-omniscience: Evaluat- ing cross-domain knowledge reliability in large language models.arXiv preprint arXiv:2511.13029, 2025.

Motif 3: Technical Report Aa-omniscience: Evaluat- ing cross-domain knowledge reliability in large language models.arXiv preprint arXiv:2511.13029, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.942934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5cfcbc-cbdb-41b1-9bc2-94807788e6d4 · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

Motif 3: Technical Report DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.947925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b4d204-c61b-4404-a55a-7273f46e0ce1 · outbound

This paper cites ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks.

Motif 3: Technical Report ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.952843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d05a1ea-4f01-4880-adce-36b5a6f98733 · outbound

This paper cites DCP: Addressing input dynamism in long-context training via dynamic context parallelism.

Motif 3: Technical Report DCP: Addressing input dynamism in long-context training via dynamic context parallelism

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.957692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608cb4a4-1909-4c77-a336-02bdd30fdb8a · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues? InInternational Conference on Learning Representations, volume 2024, pages 54107–54157, 2024.

Motif 3: Technical Report Swe-bench: Can language models resolve real-world github issues? InInternational Conference on Learning Representations, volume 2024, pages 54107–54157, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.962235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2e2b74-fd1e-488c-90a6-2d3ddfe1ccba · outbound

This paper cites Muon: An optimizer for hidden layers in neural networks.

Motif 3: Technical Report Muon: An optimizer for hidden layers in neural networks

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.562956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 03783b4a-ceea-4732-92b8-3b051137d883 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Motif 3: Technical Report Kimi K2: Open Agentic Intelligence

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.972456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e065b7b-3567-4d23-a895-c6ee4e169766 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Motif 3: Technical Report Kimi K2.5: Visual Agentic Intelligence

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.977432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0071cf32-e991-49d1-bede-73c3b89a0af7 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Motif 3: Technical Report Gonzalez, Hao Zhang, and Ion Stoica

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.982830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ca5d116-f7fb-4b0d-90d6-2ac85455ca3e · outbound

This paper cites TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training.

Motif 3: Technical Report TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.988368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3c003a-1cc6-4aa6-bfa8-fc59fbd83a1d · outbound

This paper cites Motif 2 12.7b technical report.arXiv preprint arXiv:2511.07464, 2025.

Motif 3: Technical Report Motif 2 12.7b technical report.arXiv preprint arXiv:2511.07464, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.993766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01144cd2-f180-4711-8d7e-67887affa96e · outbound

This paper cites Every step evolves: Scaling reinforcement learning for trillion-scale thinking model.arXiv preprint arXiv:2510.18855, 2025.

Motif 3: Technical Report Every step evolves: Scaling reinforcement learning for trillion-scale thinking model.arXiv preprint arXiv:2510.18855, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:09.998809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 194d245f-806a-4e4b-aa45-421f97a75a4c · outbound

This paper cites SuperBPE: Space Travel for Language Models.

Motif 3: Technical Report SuperBPE: Space Travel for Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.004036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62623cfa-e887-45df-be92-d580fb9462ee · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

Motif 3: Technical Report Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.009526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb7fa046-b61b-45ad-9634-2c906667a580 · outbound

This paper cites Muon is Scalable for LLM Training.

Motif 3: Technical Report Muon is Scalable for LLM Training

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.014334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd137cd5-4779-4fa2-9e77-d3ebc0ac8e99 · outbound

This paper cites Towards robust mathematical reasoning.

Motif 3: Technical Report Towards robust mathematical reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.019631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 638ea282-a2b2-4fbd-8cc9-111502ca2e14 · outbound

This paper cites Terminal-bench: Benchmarking agents on hard, realistic tasks in command line interfaces.

Motif 3: Technical Report Terminal-bench: Benchmarking agents on hard, realistic tasks in command line interfaces

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.523344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b5f5423a-0c9f-4548-9faa-4ef49be4751d · outbound

This paper cites Recipes for Pre-training LLMs with MXFP8.

Motif 3: Technical Report Recipes for Pre-training LLMs with MXFP8

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.029200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9449845-72c5-4ff1-a580-2de88c5682c9 · outbound

This paper cites Jordan, and Ion Stoica.

Motif 3: Technical Report Jordan, and Ion Stoica

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.504267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 65642ad7-ac59-48e1-bfc5-1ace938c1f21 · outbound

This paper cites Motif 3 training example.

Motif 3: Technical Report Motif 3 training example

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.482443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f79ac33-eac1-4e0d-893a-0f71b3cbd299 · outbound

This paper cites Scalable training of mixture-of-experts models with megatron core.arXiv preprint arXiv:2603.07685, 2026.

Motif 3: Technical Report Scalable training of mixture-of-experts models with megatron core.arXiv preprint arXiv:2603.07685, 2026

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.044081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c69914e2-01a5-4b36-9d00-c8d3757c2d83 · outbound

This paper cites Nemotron post-training v3.

Motif 3: Technical Report Nemotron post-training v3

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.462590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bf27e2ef-21f7-4b22-b3ca-33a0ed3e5e65 · outbound

This paper cites Nemotron pre-training datasets.

Motif 3: Technical Report Nemotron pre-training datasets

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.443282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f06151ac-f6c9-46e6-88f2-f881a7c2196c · outbound

This paper cites NeMo Gym: Environments for evaluating and improving models and agents.

Motif 3: Technical Report NeMo Gym: Environments for evaluating and improving models and agents

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.425302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6ee8c42a-f812-4fe4-a905-c26b76c62e5c · outbound

This paper cites NeMo RL: A scalable and efficient post-training library.

Motif 3: Technical Report NeMo RL: A scalable and efficient post-training library

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.406166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4f0b6eab-fa09-42d0-8eee-4c506f806ed5 · outbound

This paper cites Nemotron 3 Ultra: Open, efficient mixture-of-experts hybrid mamba-transformer model for agentic reasoning.arXiv preprint arXiv:2606.15007, 2026.

Motif 3: Technical Report Nemotron 3 Ultra: Open, efficient mixture-of-experts hybrid mamba-transformer model for agentic reasoning.arXiv preprint arXiv:2606.15007, 2026

Reference 48

Resolution: verified exact; doi, observed 2026-08-11T23:12:10.634258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cce1f40d-086c-48e6-b247-19cfc96c0975 · outbound

This paper cites gpt-oss: Reference implementations for gpt-oss-120b and gpt-oss-20b.

Motif 3: Technical Report gpt-oss: Reference implementations for gpt-oss-120b and gpt-oss-20b

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.386399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0e720d45-4fbf-4372-ba4a-9280a982f235 · outbound

This paper cites TorchAO: PyTorch-native training-to-serving model optimization.ICML Workshop on Championing Open-source Development, 2025.

Motif 3: Technical Report TorchAO: PyTorch-native training-to-serving model optimization.ICML Workshop on Championing Open-source Development, 2025

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.348690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5bd55e93-7cab-4b2f-9add-de6afb2e3fe8 · outbound

This paper cites Gdpval: Evaluating ai model performance on real-world economically valuable tasks.

Motif 3: Technical Report Gdpval: Evaluating ai model performance on real-world economically valuable tasks

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.331577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8d7537e0-6840-4ccc-b39f-3756a90d6595 · outbound

This paper cites Humanity's Last Exam.

Motif 3: Technical Report Humanity's Last Exam

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.100397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 658b672c-b141-44bc-8c72-634020f74e42 · outbound

This paper cites On data engineering for scaling llm terminal capabilities, 2026.

Motif 3: Technical Report On data engineering for scaling llm terminal capabilities, 2026

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.105901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130bbe81-6b5c-4f1b-82c2-3a8874152cdf · outbound

This paper cites Generalizing verifiable instruction following.Advances in Neural Information Processing Systems, 38, 2025.

Motif 3: Technical Report Generalizing verifiable instruction following.Advances in Neural Information Processing Systems, 38, 2025

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.315765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9f3b0e17-5fb2-4950-8600-2c48208ebd01 · outbound

This paper cites Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free.

Motif 3: Technical Report Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.115800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 590e99df-d25f-49e7-84fc-51ee9d765e66 · outbound

This paper cites A unified view of attention and residual sinks: Outlier-driven rescaling is essential for transformer training.arXiv preprint arXiv:2601.22966, 2026.

Motif 3: Technical Report A unified view of attention and residual sinks: Outlier-driven rescaling is essential for transformer training.arXiv preprint arXiv:2601.22966, 2026

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.128680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc397ad8-5560-48ee-88ca-4c6fcab0ce3c · outbound

This paper cites Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free.

Motif 3: Technical Report Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.121953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c20e77-eb16-4dc3-a761-18865c2bea1d · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Motif 3: Technical Report GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.138847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f3b8d8-1fb7-46bb-8a01-8fd87e5e148a · outbound

This paper cites Qwen3-Next: Towards ultimate training and inference efficiency.https://qwen.ai/ blog?id=4074cca80393150c248e508aa62983f9cb7d27cd, September 2025.

Motif 3: Technical Report Qwen3-Next: Towards ultimate training and inference efficiency.https://qwen.ai/ blog?id=4074cca80393150c248e508aa62983f9cb7d27cd, September 2025

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.299158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 90de544c-c905-4a0a-bdc2-63e3b7083dfd · outbound

This paper cites WinoGrande: An adver- sarial winograd schema challenge at scale.Proceedings of the AAAI Conference on Artificial Intelligence, 2020.

Motif 3: Technical Report WinoGrande: An adver- sarial winograd schema challenge at scale.Proceedings of the AAAI Conference on Artificial Intelligence, 2020

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.281957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 88f16c11-468e-465d-97e0-d854675b5a6f · outbound

This paper cites Microscaling Data Formats for Deep Learning.

Motif 3: Technical Report Microscaling Data Formats for Deep Learning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.143929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565090d2-b164-4bfe-b451-899deedc8326 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Motif 3: Technical Report RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.165525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48333d04-8b1c-4600-a18e-41b7daa79b4e · outbound

This paper cites τ-knowledge: Evaluating conversational agents over unstructured knowledge.arXiv preprint arXiv:2603.04370,.

Motif 3: Technical Report τ-knowledge: Evaluating conversational agents over unstructured knowledge.arXiv preprint arXiv:2603.04370,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.154236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4ebf87-4881-4c90-a692-b24580d2b981 · outbound

This paper cites Scicode: A research coding benchmark curated by scientists.

Motif 3: Technical Report Scicode: A research coding benchmark curated by scientists

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.263876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 04c7a0ca-2322-4b10-8f51-e40767904f10 · outbound

This paper cites Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts.

Motif 3: Technical Report Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.183916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51eec268-e592-44dc-924e-ce6a116d184f · outbound

This paper cites Grouped differential attention.arXiv preprint arXiv:2510.06949, 2025.

Motif 3: Technical Report Grouped differential attention.arXiv preprint arXiv:2510.06949, 2025

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.171334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a88bcdc-bf30-4dce-bd24-8813af3a57db · outbound

This paper cites MiMo-V2-Flash Technical Report.

Motif 3: Technical Report MiMo-V2-Flash Technical Report

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.194310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56d9fe3b-f351-46a0-98fe-19a3e70a3d33 · outbound

This paper cites mHC: Manifold-Constrained Hyper-Connections.

Motif 3: Technical Report mHC: Manifold-Constrained Hyper-Connections

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.200467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4283f41e-ee27-4cf0-a41e-cf74fe4107e5 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Motif 3: Technical Report MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.189128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffd0b996-51c0-41a8-8970-e8ca0bcbc285 · outbound

This paper cites Differential Transformer.

Motif 3: Technical Report Differential Transformer

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.212539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb82c6f1-1220-44de-9e27-cfd765db5d69 · outbound

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

Motif 3: Technical Report DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.219549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45f55783-e7a0-4d88-ac15-aff26dbe55d6 · outbound

This paper cites Qwen3 Technical Report.

Motif 3: Technical Report Qwen3 Technical Report

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.206551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ae2597-b3ff-49f5-8d85-f660c0340cbf · outbound

This paper cites HellaSwag: Can a machine really finish your sentence?Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019.

Motif 3: Technical Report HellaSwag: Can a machine really finish your sentence?Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.247609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ce6ea7e8-7939-4eb5-aabb-4d35bab167b3 · outbound

This paper cites Root Mean Square Layer Normalization.

Motif 3: Technical Report Root Mean Square Layer Normalization

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.237953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be72b3b2-2e39-439b-a457-401f577ca6fc · outbound

This paper cites FlashAttention-4: Algorithm and kernel pipelining co-design for asymmetric hardware scaling.

Motif 3: Technical Report FlashAttention-4: Algorithm and kernel pipelining co-design for asymmetric hardware scaling

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.226491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf7eaa0-a3fb-4bf7-a84c-d0a9f0a7c522 · outbound

This paper cites Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark.

Motif 3: Technical Report Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T23:12:10.251313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 742f5b50-d7ae-4c5e-941d-5c718e20fb1f · outbound

This paper cites [ˆ\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}]*[\p{Ll}\p{Lm}\p{Lo}\p{M}]+.

Motif 3: Technical Report [ˆ\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}]*[\p{Ll}\p{Lm}\p{Lo}\p{M}]+

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.213039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 090c824f-4a9c-472a-92ff-8136d99e22bb · outbound

This paper cites Gonzalez, Clark Barrett, and Ying Sheng.

Motif 3: Technical Report Gonzalez, Clark Barrett, and Ying Sheng

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:12:12.229861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e207c589-2198-4d99-bb29-b737b23e5835 · outbound

This paper cites an unresolved cited work.

Motif 3: Technical Report Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-11T23:12:12.365678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c73b670a-145d-4993-b16a-88cb5e224723 · outbound

This paper cites an unresolved cited work.

Motif 3: Technical Report Unresolved cited work

Reference 2026

Resolution: verified exact; doi, observed 2026-08-11T23:12:10.523657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers