Paper Citation Record · LEDGER

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

As of 4 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 19 inbound Pith citation observations for arXiv:2605.26494.

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

pith.paper-citation-record.v1
2605.26494 v2

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T13:10:20.456135Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T15:38:30.265209Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T13:57:07.070944Z

Reference resolution

6 of 6 outbound references displayed

verified exact0
verified fuzzy0
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1a92c811-73eb-46d8-b43b-75288e783cba · outbound

This paper cites GQA: Training generalized multi-query transformer models from multi-head checkpoints.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence GQA: Training generalized multi-query transformer models from multi-head checkpoints

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:19.731765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30435a4e-c681-4105-8555-c04f669fdae7 · outbound

This paper cites American invitational mathematics examination 2025.https: //www.maa.org/math-competitions/aime,.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence American invitational mathematics examination 2025.https: //www.maa.org/math-competitions/aime,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:20.129935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1d7a23-6941-4050-a417-8a69e51c95a0 · outbound

This paper cites American invitational mathematics examination 2026.https: //www.maa.org/math-competitions/aime,.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence American invitational mathematics examination 2026.https: //www.maa.org/math-competitions/aime,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:20.286670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c19612f9-097d-406c-9640-cb71bb619ac5 · outbound

This paper cites Wide Search: Benchmarking long-horizon multi-source web research, 2025a.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Wide Search: Benchmarking long-horizon multi-source web research, 2025a

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:20.008563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f42c610-7ba1-4f74-808d-c39a1bc297d0 · outbound

This paper cites Le, Ed H.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Le, Ed H

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:20.456135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 736873a4-0873-46d0-8260-67f7716fb788 · outbound

This paper cites Dive: Scalingdiversityinagentictasksynthesisforgeneralizable tool use.arXiv preprint arXiv:2603.11076,.

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Dive: Scalingdiversityinagentictasksynthesisforgeneralizable tool use.arXiv preprint arXiv:2603.11076,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T13:10:19.860287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6de01c2b-910e-475c-8523-985dab72257b · inbound

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models cites this paper.

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:06:21.105338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7cfb61e7-0ec3-4a77-87d8-adc780232bc2 · inbound

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents cites this paper.

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-02T13:36:59.490369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d5972ae3-0910-4849-88b7-6cb0de1f05cf · inbound

OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents cites this paper.

OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-03T11:58:06.904405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 983a1e56-8f13-4b9e-b5da-9e15c657a09d · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-04T05:09:36.884347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 28e88532-8b0d-4dfb-98ae-1692befcf0fa · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T10:49:02.690693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7db96de-d7ab-44b4-8d4a-c571289b0eae · inbound

CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents cites this paper.

CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-04T10:39:44.814892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 503164c9-3234-4cc9-b0cb-6c0b5de6bf36 · inbound

INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models cites this paper.

INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:19:49.112184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f8ab29d3-b49a-4d5c-8c2a-f4af4bfa4af8 · inbound

Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems cites this paper.

Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 54

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T13:57:07.072526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6af5bdb8-9200-4dc6-b476-6123b0ba3cd7 · inbound

When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability cites this paper.

When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-10T05:56:50.514836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f7d69252-47d5-43e1-a32c-361f9031b298 · inbound

Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detection cites this paper.

Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detection The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T18:14:39.947220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3857960-05af-4d4d-9f43-65e1d59ceeba · inbound

ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders cites this paper.

ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T08:11:26.622369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a63bafd-7342-4889-abcf-deb3614d4e54 · inbound

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization cites this paper.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T05:09:54.047136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 334e3c4e-31eb-41a9-af80-015a5ce95cda · inbound

Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents cites this paper.

Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T18:50:51.326411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d29c48-fd02-4568-80ea-8db2a3562d85 · inbound

AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification cites this paper.

AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T00:25:12.123904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a410feff-cd3e-4a6e-93f1-ddb03dec35a5 · inbound

DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness cites this paper.

DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T19:54:08.495514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01ff39f7-4134-4fe8-a093-fd46a1324a0c · inbound

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation cites this paper.

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T07:20:10.826590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77ce4a6a-8f19-4448-b5da-6b341055f233 · inbound

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation cites this paper.

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:29.985791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5139b2e-c09d-4c62-b2eb-07db4cafe6c8 · inbound

Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning cites this paper.

Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-31T06:09:53.789633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1396abb0-8f61-40f0-a41a-88a3d5fec0c8 · inbound

MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents cites this paper.

MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T15:38:30.265209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.