Paper Citation Record · LEDGER

Scaling Native Multimodal Pre-Training From Scratch

As of 10 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2607.22043.

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

pith.paper-citation-record.v1
2607.22043 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T06:05:51.822157Z

measured 22 of 22 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:08:56.542757Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T11:55:28.599019Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved19
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 856c3335-7f7d-4384-b7a3-a456a6083ad4 · outbound

This paper cites B Experiment Results This section details the comprehensive per-benchmark results supporting the analyses presented in Section 4, organized into three primary categories.

Scaling Native Multimodal Pre-Training From Scratch B Experiment Results This section details the comprehensive per-benchmark results supporting the analyses presented in Section 4, organized into three primary categories

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-08-01T06:05:51.822157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead061e3-8709-4d91-b02a-fdde4282e2bf · outbound

This paper cites SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines.

Scaling Native Multimodal Pre-Training From Scratch SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.162416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e85c9bb8-a03c-4297-808f-ef5efe7d45ef · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Scaling Native Multimodal Pre-Training From Scratch TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.526418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd9c77e-1b29-4b8a-90f5-239837ed3207 · outbound

This paper cites SocialIQA: Commonsense Reasoning about Social Interactions.

Scaling Native Multimodal Pre-Training From Scratch SocialIQA: Commonsense Reasoning about Social Interactions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.965502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f1ed92-845b-42d2-b20c-d7589845fe0d · outbound

This paper cites CountQA: How Well Do MLLMs Count in the Wild?.

Scaling Native Multimodal Pre-Training From Scratch CountQA: How Well Do MLLMs Count in the Wild?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.176081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 614566c2-0175-4d9a-aa16-8704f6bdfed6 · outbound

This paper cites Beyond Language Modeling: An Exploration of Multimodal Pretraining.

Scaling Native Multimodal Pre-Training From Scratch Beyond Language Modeling: An Exploration of Multimodal Pretraining

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.300505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be91083e-1d09-4308-a721-39023b8eb3ee · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

Scaling Native Multimodal Pre-Training From Scratch SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.388385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37482601-c0a9-4281-8423-757addebef24 · outbound

This paper cites LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts.

Scaling Native Multimodal Pre-Training From Scratch LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.483271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cbdd42e-40b8-47ee-b422-847ec4b20f7f · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

Scaling Native Multimodal Pre-Training From Scratch HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.578252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0299e798-3028-48b6-9547-ec7c6453b70c · outbound

This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.

Scaling Native Multimodal Pre-Training From Scratch AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.646144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e62a012-efbd-40a0-969e-fc653e72f039 · outbound

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

Scaling Native Multimodal Pre-Training From Scratch Kimi K2.5: Visual Agentic Intelligence

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.744535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c65647e-5163-42cb-9a4d-fc7daf5f8f56 · outbound

This paper cites Scaling Laws for Neural Language Models.

Scaling Native Multimodal Pre-Training From Scratch Scaling Laws for Neural Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.633139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c06469c9-7efd-4bf6-bd39-c9338a0f66c5 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Scaling Native Multimodal Pre-Training From Scratch Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.077650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eca071a0-9487-4488-8b9e-a93547fca486 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Scaling Native Multimodal Pre-Training From Scratch Training Compute-Optimal Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.323293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72283a80-6ac1-414d-989d-5a71c8d3f60f · outbound

This paper cites Emu3.5: Native Multimodal Models are World Learners.

Scaling Native Multimodal Pre-Training From Scratch Emu3.5: Native Multimodal Models are World Learners

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.098846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0024aedb-602f-46ae-9c12-c734a14323da · outbound

This paper cites OmniS- patial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models.arXiv preprint arXiv:2506.03135,.

Scaling Native Multimodal Pre-Training From Scratch OmniS- patial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models.arXiv preprint arXiv:2506.03135,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.428860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d8c3356-65c3-4221-bd68-e3cb80d0dd06 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Scaling Native Multimodal Pre-Training From Scratch Measuring Massive Multitask Language Understanding

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.263534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cd0fced-9622-4c04-9a67-8736f94141b9 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Scaling Native Multimodal Pre-Training From Scratch Training Verifiers to Solve Math Word Problems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.023614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f40d8a51-4782-428a-9029-7ee9b258ee8e · outbound

This paper cites DeepSeek-V3 Technical Report.

Scaling Native Multimodal Pre-Training From Scratch DeepSeek-V3 Technical Report

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:50.854597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57737de-fe33-415e-896e-4766186d75d6 · outbound

This paper cites We detail the specific architecture configurations and training settings in Table.

Scaling Native Multimodal Pre-Training From Scratch We detail the specific architecture configurations and training settings in Table

Reference 4096

Resolution: unresolved; no resolver link, observed 2026-08-01T06:05:51.724178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 41f0d0e1-821b-4096-8db3-3eb8253c53e9 · inbound

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes cites this paper.

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Scaling Native Multimodal Pre-Training From Scratch

Reference 137

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:55:28.602138Z

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 6af140f3-9e6d-4d4f-af84-5cd5400e99c6 · inbound

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes cites this paper.

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Scaling Native Multimodal Pre-Training From Scratch

Reference 137

Resolution: unresolved; no resolver link, observed 2026-08-08T17:08:56.542757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.