Paper Citation Record · LEDGER

KAT-V1: Kwai-AutoThink Technical Report

As of 7 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2507.08297.

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

pith.paper-citation-record.v1
2507.08297 v3

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:28:31.763652Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:42:21.114924Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T14:42:21.257284Z

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy13
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation df6293d8-b8ad-48bb-a257-d401ef5144ee · outbound

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

KAT-V1: Kwai-AutoThink Technical Report DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:27.498496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af7d74f-259a-4352-b98f-b94de0aac534 · outbound

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

KAT-V1: Kwai-AutoThink Technical Report DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:27.557422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39082e59-7523-46ae-90ca-fc0b662bcf0c · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

KAT-V1: Kwai-AutoThink Technical Report DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:27.693211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd36adf-a2a0-4851-8d98-1b0102eae9cb · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

KAT-V1: Kwai-AutoThink Technical Report DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:27.826209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37994a6b-b5a4-47d2-8e34-010cc582dcd7 · outbound

This paper cites Qwen3 Technical Report.

KAT-V1: Kwai-AutoThink Technical Report Qwen3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:27.963650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b68b8b0b-c2e4-4af5-a220-6f56c3de64ea · outbound

This paper cites Qwen2.5 technical report, 2025.

KAT-V1: Kwai-AutoThink Technical Report Qwen2.5 technical report, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.069380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3b4bb2d-6db6-43cb-b900-dc3fee507080 · outbound

This paper cites Qwen2 technical report, 2024.

KAT-V1: Kwai-AutoThink Technical Report Qwen2 technical report, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.146933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 653eddec-8234-4c31-924c-8790c73cd6c3 · outbound

This paper cites Qwen Technical Report.

KAT-V1: Kwai-AutoThink Technical Report Qwen Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.212924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 206941bf-ea76-40f9-8fa2-4d75be2c54d9 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai inno- vation.

KAT-V1: Kwai-AutoThink Technical Report The llama 4 herd: The beginning of a new era of natively multimodal ai inno- vation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:34.850544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 742eacc5-f932-4c65-a033-6e5b3dc80190 · outbound

This paper cites The Llama 3 Herd of Models.

KAT-V1: Kwai-AutoThink Technical Report The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.549505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0464e130-857d-4970-8702-4dfea5d899f8 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

KAT-V1: Kwai-AutoThink Technical Report Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.638031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e012ba48-fb23-476c-a35e-3e2fe6ccd326 · outbound

This paper cites MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models.

KAT-V1: Kwai-AutoThink Technical Report MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.753626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b689633-bd08-456d-94c1-81c78a624f73 · outbound

This paper cites A comprehensive survey on long context language modeling.

KAT-V1: Kwai-AutoThink Technical Report A comprehensive survey on long context language modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:28.901478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93c864e8-0719-4dec-8ba7-15a36f7a62d5 · outbound

This paper cites M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation.

KAT-V1: Kwai-AutoThink Technical Report M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.016177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb3e5c8-a43e-4f28-acff-326768ede098 · outbound

This paper cites R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models.

KAT-V1: Kwai-AutoThink Technical Report R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.123556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b7e412-e66e-406f-9421-544bd614a400 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

KAT-V1: Kwai-AutoThink Technical Report Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.186958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a811da9d-68ac-4211-96e5-92ec16c1edab · outbound

This paper cites Concise reason- ing via reinforcement learning.

KAT-V1: Kwai-AutoThink Technical Report Concise reason- ing via reinforcement learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.243344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d8e1119-11b2-45b6-9163-7a84a6791055 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

KAT-V1: Kwai-AutoThink Technical Report Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.360176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9366b63d-c32d-4685-aa52-fe7a75cf065d · outbound

This paper cites AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning.

KAT-V1: Kwai-AutoThink Technical Report AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.506916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee207456-fbe3-4f58-ae61-6c7c64b52dd9 · outbound

This paper cites Think Only When You Need with Large Hybrid-Reasoning Models.

KAT-V1: Kwai-AutoThink Technical Report Think Only When You Need with Large Hybrid-Reasoning Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.688777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe65655-e6ef-4284-bd57-2d0231e6b8fd · outbound

This paper cites Thinkless: LLM Learns When to Think.

KAT-V1: Kwai-AutoThink Technical Report Thinkless: LLM Learns When to Think

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.779954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a4d10b-1457-4876-bc65-57fb3c990cb6 · outbound

This paper cites Learning when to think: Shaping adaptive reasoning in r1-style models via multi-stage rl.

KAT-V1: Kwai-AutoThink Technical Report Learning when to think: Shaping adaptive reasoning in r1-style models via multi-stage rl

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.855822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741910ae-913f-4c41-b24c-e439b6b1f449 · outbound

This paper cites AdaptThink: Reasoning Models Can Learn When to Think.

KAT-V1: Kwai-AutoThink Technical Report AdaptThink: Reasoning Models Can Learn When to Think

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.917410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c4e177-98d1-494f-bac1-6a01397ac3b8 · outbound

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

KAT-V1: Kwai-AutoThink Technical Report DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.991061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2df3dae-67e9-4e7d-817f-5258b8c4f937 · outbound

This paper cites Proximal Policy Optimization Algorithms.

KAT-V1: Kwai-AutoThink Technical Report Proximal Policy Optimization Algorithms

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.104343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f2a635-f86a-4f5a-879b-26846a248205 · outbound

This paper cites Knowledge distillation: A survey.

KAT-V1: Kwai-AutoThink Technical Report Knowledge distillation: A survey

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.194557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db88f0c5-5659-47a9-871c-2b9d1b63fe4a · outbound

This paper cites Distilling the Knowledge in a Neural Network.

KAT-V1: Kwai-AutoThink Technical Report Distilling the Knowledge in a Neural Network

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.244737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2112b756-3c29-4bd6-b8c4-0305d53be76b · outbound

This paper cites Ddk: Distilling domain knowledge for efficient large language models.

KAT-V1: Kwai-AutoThink Technical Report Ddk: Distilling domain knowledge for efficient large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:34.666846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 04bad843-450f-4b5d-81a0-0b5eba50a237 · outbound

This paper cites DeepSeek-V3 Technical Report.

KAT-V1: Kwai-AutoThink Technical Report DeepSeek-V3 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.376076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e16bb927-3e76-40a4-91cc-875e83af6f8a · outbound

This paper cites SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM.

KAT-V1: Kwai-AutoThink Technical Report SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.436815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6441f73-7418-4a7f-bc11-cf2744d4ac69 · outbound

This paper cites Livecodebench pro: How do olympiad medalists judge llms in competitive programming?, 2025.

KAT-V1: Kwai-AutoThink Technical Report Livecodebench pro: How do olympiad medalists judge llms in competitive programming?, 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:34.485559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d7c6d704-8629-42bb-b7cd-587f59831ca4 · outbound

This paper cites Introduction to techniques used in seed1.6.

KAT-V1: Kwai-AutoThink Technical Report Introduction to techniques used in seed1.6

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:34.322767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62493af4-5edc-451b-a85d-ae9f5fff9b99 · outbound

This paper cites Introducing openai o3-mini.

KAT-V1: Kwai-AutoThink Technical Report Introducing openai o3-mini

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:34.118900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c5910ea4-34db-4eab-a3c5-ae7b19d124e4 · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

KAT-V1: Kwai-AutoThink Technical Report Yi: Open Foundation Models by 01.AI

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.801945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e58c0ffe-f16c-42b3-b8ac-ecef3e38d59b · outbound

This paper cites Llama-nemotron: Efficient reasoning models, 2025.

KAT-V1: Kwai-AutoThink Technical Report Llama-nemotron: Efficient reasoning models, 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.990962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e5eeaa8f-8f2b-456e-8220-84ff31c598b7 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

KAT-V1: Kwai-AutoThink Technical Report Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:30.957011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d212d7b-df23-4154-b05c-7424be6d2047 · outbound

This paper cites DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs.

KAT-V1: Kwai-AutoThink Technical Report DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.766165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 07c72986-055d-40cc-b147-1df613ae4cbe · outbound

This paper cites Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024.

KAT-V1: Kwai-AutoThink Technical Report Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:31.104895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5858b0-7c73-45e9-aab4-9b4ad52aa01e · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

KAT-V1: Kwai-AutoThink Technical Report Gpqa: A graduate-level google-proof q&a benchmark

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:31.185978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6833591c-79f6-4ef3-bddf-ca7503074d35 · outbound

This paper cites Math-500 dataset.

KAT-V1: Kwai-AutoThink Technical Report Math-500 dataset

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.590441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ce2cd7cb-d208-49ab-a0f1-a88f4c136b77 · outbound

This paper cites Aime_2024 dataset.

KAT-V1: Kwai-AutoThink Technical Report Aime_2024 dataset

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.451575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 53a26be4-b108-4200-8e5f-1ca7be795f44 · outbound

This paper cites Aime2025 dataset.

KAT-V1: Kwai-AutoThink Technical Report Aime2025 dataset

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.223468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d64594a5-225a-49b7-92e7-64979b6f5381 · outbound

This paper cites Autologi: Automated generation of logic puzzles for evaluating reasoning abilities of large language models, 2025.

KAT-V1: Kwai-AutoThink Technical Report Autologi: Automated generation of logic puzzles for evaluating reasoning abilities of large language models, 2025

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:33.049895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c6bf2d8-93ea-498e-8513-4d94ee11fd63 · outbound

This paper cites an unresolved cited work.

KAT-V1: Kwai-AutoThink Technical Report Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:28:32.844954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 19bd6725-d6a6-4e28-8c64-c8be83c87cf1 · outbound

This paper cites Program Synthesis with Large Language Models.

KAT-V1: Kwai-AutoThink Technical Report Program Synthesis with Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:31.650019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 603878f0-7d62-4007-bc62-f0a4fd641460 · outbound

This paper cites Livecodebench: Holistic and con- tamination free evaluation of large language models for code.

KAT-V1: Kwai-AutoThink Technical Report Livecodebench: Holistic and con- tamination free evaluation of large language models for code

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:32.665296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation caa099e6-cd6d-488c-96b3-d61582477456 · outbound

This paper cites Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E.

KAT-V1: Kwai-AutoThink Technical Report Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:28:32.552556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation ee06b167-3ef6-4ae8-b4a5-f26f18987766 · inbound

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning cites this paper.

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning KAT-V1: Kwai-AutoThink Technical Report

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:42:21.261957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.