Paper Citation Record · LEDGER

VLMs Can Aggregate Scattered Training Patches

As of 24 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2506.03614.

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

pith.paper-citation-record.v1
2506.03614 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:04:05.900085Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact3
verified fuzzy11
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9a127931-f64f-40df-b243-a246c97ac1a4 · outbound

This paper cites Openai moderation api.

VLMs Can Aggregate Scattered Training Patches Openai moderation api

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.424348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 65e24ab1-c7ac-455e-aa23-7e62da3a9055 · outbound

This paper cites Large Language Models are Limited in Out-of-Context Knowledge Reasoning.

VLMs Can Aggregate Scattered Training Patches Large Language Models are Limited in Out-of-Context Knowledge Reasoning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:04:06.281794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aa1c3d5c-568f-4b90-9fa5-156c0a444a93 · outbound

This paper cites Reverse Thinking Makes LLMs Stronger Reasoners.

VLMs Can Aggregate Scattered Training Patches Reverse Thinking Makes LLMs Stronger Reasoners

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.772059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91a8c0ae-eea5-4b4f-894e-4dbd963bdbcf · outbound

This paper cites Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training.

VLMs Can Aggregate Scattered Training Patches Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:04:06.261535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c141d448-78b1-4388-8cee-1e9679717e2c · outbound

This paper cites Reverse Training to Nurse the Reversal Curse.

VLMs Can Aggregate Scattered Training Patches Reverse Training to Nurse the Reversal Curse

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.778690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbcdc408-2858-4387-b2de-4f0f7afb3668 · outbound

This paper cites Towards a theoretical understanding of the’reversal curse’via training dynamics.

VLMs Can Aggregate Scattered Training Patches Towards a theoretical understanding of the’reversal curse’via training dynamics

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.416371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 488a4405-6b0e-4d97-bd2b-4621e6360a1b · outbound

This paper cites Is the reversal curse a binding problem? uncovering limitations of transformers from a basic generalization failure.

VLMs Can Aggregate Scattered Training Patches Is the reversal curse a binding problem? uncovering limitations of transformers from a basic generalization failure

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.785202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad14d7a-bed1-4286-be12-d33bd9948047 · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

VLMs Can Aggregate Scattered Training Patches Tell me about yourself: LLMs are aware of their learned behaviors

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.788018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984829d6-5a12-4e9e-9eda-6e07cec21d3c · outbound

This paper cites Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts.

VLMs Can Aggregate Scattered Training Patches Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.791113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db817033-1b2e-405c-8760-ff9216184b57 · outbound

This paper cites a is b” fail to learn “b is a.

VLMs Can Aggregate Scattered Training Patches a is b” fail to learn “b is a

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.407898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5ccd6c34-520b-43b1-af70-6938e5fc7a5d · outbound

This paper cites Physics of Language Models: Part 3.2, Knowledge Manipulation.

VLMs Can Aggregate Scattered Training Patches Physics of Language Models: Part 3.2, Knowledge Manipulation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.797313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ada3cfcb-d30e-47bd-8629-1dc8b67400f5 · outbound

This paper cites Connecting the dots: Llms can infer and verbalize latent structure from disparate training data.

VLMs Can Aggregate Scattered Training Patches Connecting the dots: Llms can infer and verbalize latent structure from disparate training data

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.398839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 28a28093-5e1f-4347-8759-7201ee503c51 · outbound

This paper cites Me, myself, and ai: The situational awareness dataset (sad) for llms.Advances in Neural Information Processing Systems, 37:64010– 64118, 2024.

VLMs Can Aggregate Scattered Training Patches Me, myself, and ai: The situational awareness dataset (sad) for llms.Advances in Neural Information Processing Systems, 37:64010– 64118, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.390131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bded0a98-0829-4e4f-aa2a-29b7e4584e5b · outbound

This paper cites Taken out of context: On measuring situational awareness in LLMs.

VLMs Can Aggregate Scattered Training Patches Taken out of context: On measuring situational awareness in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.805625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb34019a-eddd-46f1-be21-5ac66b7eeb05 · outbound

This paper cites From Imitation to Introspection: Probing Self-Consciousness in Language Models.

VLMs Can Aggregate Scattered Training Patches From Imitation to Introspection: Probing Self-Consciousness in Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.808656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55571521-cb08-4134-ac95-361279f3394e · outbound

This paper cites The Llama 3 Herd of Models.

VLMs Can Aggregate Scattered Training Patches The Llama 3 Herd of Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.811328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35a02ad-b254-4a57-94f0-b68babaeec41 · outbound

This paper cites Gemma 3 Technical Report.

VLMs Can Aggregate Scattered Training Patches Gemma 3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.814660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513fb847-4e87-4aea-995d-80b531f0503d · outbound

This paper cites ShieldGemma 2: Robust and Tractable Image Content Moderation.

VLMs Can Aggregate Scattered Training Patches ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.817517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f196d9-71c2-43b6-9217-26debf298a97 · outbound

This paper cites Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations.

VLMs Can Aggregate Scattered Training Patches Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.820412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53552460-c4e4-402a-a4bc-6b84be6d8787 · outbound

This paper cites MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks.

VLMs Can Aggregate Scattered Training Patches MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.823376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5719697c-4c9d-4267-b964-5a02d0222927 · outbound

This paper cites Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency.

VLMs Can Aggregate Scattered Training Patches Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.826344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8998835d-025d-4c26-9991-a3953ac83b64 · outbound

This paper cites Composite Backdoor Attacks Against Large Language Models.

VLMs Can Aggregate Scattered Training Patches Composite Backdoor Attacks Against Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.829192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b59a7cf-4d8d-4389-a951-766f8d36afb1 · outbound

This paper cites Jailbreaking large language models against moderation guardrails via cipher characters.

VLMs Can Aggregate Scattered Training Patches Jailbreaking large language models against moderation guardrails via cipher characters

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.381296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 06439815-8343-4924-a34d-d63b1a79e6ce · outbound

This paper cites Sugar-coated poison: Benign generation unlocks llm jailbreaking.

VLMs Can Aggregate Scattered Training Patches Sugar-coated poison: Benign generation unlocks llm jailbreaking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.834985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ab7928-03f5-4ed6-a6d5-3d8613a27f97 · outbound

This paper cites Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing.

VLMs Can Aggregate Scattered Training Patches Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:04:05.993157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 96c212dc-b292-4ce9-87b5-7de866873984 · outbound

This paper cites Imagenet large scale visual recognition challenge.

VLMs Can Aggregate Scattered Training Patches Imagenet large scale visual recognition challenge

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.372046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 07003b75-4a1f-4006-b545-07371fa36acb · outbound

This paper cites Food-101 – mining discriminative components with random forests.

VLMs Can Aggregate Scattered Training Patches Food-101 – mining discriminative components with random forests

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.362580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d32e231-fb97-4fed-802c-8989a62d9088 · outbound

This paper cites Qwen2 Technical Report.

VLMs Can Aggregate Scattered Training Patches Qwen2 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.846569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4e3c6b5-40b2-42b2-905d-99e6d8b408c1 · outbound

This paper cites Qwen2.5 Technical Report.

VLMs Can Aggregate Scattered Training Patches Qwen2.5 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.849388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4727461-a149-4bd3-a45b-6ea9595f4598 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

VLMs Can Aggregate Scattered Training Patches InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.852456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb2759f-366d-4cf7-b453-4676af3779fe · outbound

This paper cites Improved baselines with visual instruction tuning.

VLMs Can Aggregate Scattered Training Patches Improved baselines with visual instruction tuning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.855884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09874d8c-d230-4e25-9072-e1fb28eded99 · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

VLMs Can Aggregate Scattered Training Patches Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.859421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04e58b18-7024-47cb-b6f8-0b722e79d59c · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

VLMs Can Aggregate Scattered Training Patches Imagenet classification with deep convolutional neural networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.862288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5412c0b3-aa85-457f-beb8-f8bc88e77c2b · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.

VLMs Can Aggregate Scattered Training Patches Roformer: Enhanced transformer with rotary position embedding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.865471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c73620c-82b9-486e-b12c-d4f0840f29ad · outbound

This paper cites Gemini: A family of highly capable multimodal models, 2024.

VLMs Can Aggregate Scattered Training Patches Gemini: A family of highly capable multimodal models, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.333315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7efb2fcf-024b-4828-9056-4995e17441fa · outbound

This paper cites Gpt-4o system card, 2024.

VLMs Can Aggregate Scattered Training Patches Gpt-4o system card, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.871383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91228511-7378-4407-9912-f77c9540ccb2 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

VLMs Can Aggregate Scattered Training Patches An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.874179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1b7ff7e-292a-4883-9a1e-bb014b2a47f0 · outbound

This paper cites Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model.

VLMs Can Aggregate Scattered Training Patches Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.877054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c348e8-3025-42c2-95ce-e618fc9bb59d · outbound

This paper cites Sigmoid loss for language image pre-training.

VLMs Can Aggregate Scattered Training Patches Sigmoid loss for language image pre-training

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.880064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c860655-44ff-4f93-9c1a-fe268c605c16 · outbound

This paper cites Learning transferable visual models from natural language supervision.

VLMs Can Aggregate Scattered Training Patches Learning transferable visual models from natural language supervision

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.882872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fae775-c58d-4795-95af-96d3eb607502 · outbound

This paper cites Instruction Tuning with GPT-4.

VLMs Can Aggregate Scattered Training Patches Instruction Tuning with GPT-4

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.885570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62fd9029-00aa-45e7-9f10-70256891cef4 · outbound

This paper cites Im2text: Describing images using 1 million captioned photographs.

VLMs Can Aggregate Scattered Training Patches Im2text: Describing images using 1 million captioned photographs

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.309450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4fd8c227-9b3c-4e09-a82d-c9e669920041 · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning.

VLMs Can Aggregate Scattered Training Patches Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:04:06.300777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f251a5d8-9d63-482b-a86f-1cf6d979c51c · outbound

This paper cites Trl: Transformer reinforce- ment learning.

VLMs Can Aggregate Scattered Training Patches Trl: Transformer reinforce- ment learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.894357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc14a1d-f962-4f37-993c-2fb71446a2c8 · outbound

This paper cites Zero: Memory optimiza- tions toward training trillion parameter models.

VLMs Can Aggregate Scattered Training Patches Zero: Memory optimiza- tions toward training trillion parameter models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.897315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a08ab5a-9e96-4119-91cb-b1fa091d1f52 · outbound

This paper cites MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models.

VLMs Can Aggregate Scattered Training Patches MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.900085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.