Paper Citation Record · LEDGER

The Devil is in the EOS: Sequence Training for Detailed Image Captioning

As of 17 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2507.20077.

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

pith.paper-citation-record.v1
2507.20077 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:54:07.515977Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

40 of 40 outbound references displayed

verified exact5
verified fuzzy8
unresolved26
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0624d9cb-9611-49e4-a0c4-6ab2837250a3 · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning PaliGemma: A versatile 3B VLM for transfer

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.322798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f358341f-b779-4f69-a7b9-07b20b28f586 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.328336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce59b7fb-8c53-4bfc-b2f0-6ba1f2fa19ba · outbound

This paper cites Fine-grained Image Captioning with CLIP Reward.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Fine-grained Image Captioning with CLIP Reward

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.333485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3da41f1-2963-478f-a434-db4a76722e28 · outbound

This paper cites The Algebraic Theory of Context-Free Languages.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning The Algebraic Theory of Context-Free Languages

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.339079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6582daf6-ea7e-44e8-9f6c-13f669ff27d0 · outbound

This paper cites Benchmarking and Improving Detail Image Caption.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Benchmarking and Improving Detail Image Caption

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.344293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f910008-b06e-42b0-b43b-ef48e466b577 · outbound

This paper cites CapWAP: Captioning with a Purpose.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning CapWAP: Captioning with a Purpose

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:54:08.121936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b2005623-1644-43a5-aa77-1e458d9424b2 · outbound

This paper cites No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:54:08.099843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b01f437d-ef05-459b-836a-5b633010f21e · outbound

This paper cites From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.361098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde5ebe1-0b55-4482-a6f5-c4a4bb08bae0 · outbound

This paper cites The Curious Case of Neural Text Degeneration.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning The Curious Case of Neural Text Degeneration

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.365635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a85df6d-5bd8-47dc-b4a1-87549b3cf755 · outbound

This paper cites Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:54:08.062032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a2ec6674-1c81-4224-8c2e-86bab710e7e4 · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.375622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3122664a-de87-4942-acba-29a20441971b · outbound

This paper cites Microsoft COCO: Common Objects in Context.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Microsoft COCO: Common Objects in Context

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.341967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0ffa2db8-6a74-444f-9842-c0c86a806556 · outbound

This paper cites Visual Instruction Tuning.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Visual Instruction Tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.384973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103392dd-e5f8-4691-b8fc-a3279d61d8aa · outbound

This paper cites Discriminability Objective for Training Descriptive Captions.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Discriminability Objective for Training Descriptive Captions

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.325668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation acb5cc9e-175f-461c-a20d-4bdab1a92b19 · outbound

This paper cites The EOS Decision and Length Extrapolation.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning The EOS Decision and Length Extrapolation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.394493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da94358b-cf95-47e1-bf17-41bb902efa3f · outbound

This paper cites DOCCI: Descriptions of Connected and Contrasting Images.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning DOCCI: Descriptions of Connected and Contrasting Images

Reference 16

Resolution: verified exact; doi, observed 2026-08-15T17:54:07.565999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9663f285-fd72-497a-a68d-781ff26ede28 · outbound

This paper cites GPT-4V Technical Report , 2023.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning GPT-4V Technical Report , 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.309142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0aed9076-92a6-418d-9836-e065dfd2bc7d · outbound

This paper cites ALOHa: A New Measure for Hallucination in Captioning Models.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning ALOHa: A New Measure for Hallucination in Captioning Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.409165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3adcb4a1-18f9-40fc-8f84-5cce86468310 · outbound

This paper cites Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.413999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513da7fb-1789-476f-949e-29ae254f1f06 · outbound

This paper cites Sequence Level Training with Recurrent Neural Networks.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Sequence Level Training with Recurrent Neural Networks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.419117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b08276-ca49-45ee-9679-ea7b4a613893 · outbound

This paper cites Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, and Vaibhava Goel.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, and Vaibhava Goel

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.292646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2515554f-2d20-4695-8696-935fc4fe77fb · outbound

This paper cites Object Hallucination in Image Captioning.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Object Hallucination in Image Captioning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.428543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b33775-fc13-45a1-b809-616da9dad5de · outbound

This paper cites CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.433172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f1e6ad-7c88-4317-bf25-ac39b0323c24 · outbound

This paper cites From Pixels to Prose: A Large Dataset of Dense Image Captions.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning From Pixels to Prose: A Large Dataset of Dense Image Captions

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.438008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396b9d9c-d248-4e5e-9170-a755796b90c2 · outbound

This paper cites Contrastive Search Is What You Need For Neural Text Generation.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Contrastive Search Is What You Need For Neural Text Generation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.442672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c495e41-7127-4fbe-8353-39c7f1492d5f · outbound

This paper cites A Picture is Worth More than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning A Picture is Worth More than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.276416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b3a24ac9-6b6e-48aa-a166-c96c4f413fd8 · outbound

This paper cites CIDEr: Consensus-based Image Description Evaluation.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning CIDEr: Consensus-based Image Description Evaluation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.451834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd32f109-310d-4f9f-abe3-7f1cc89215c6 · outbound

This paper cites Show and Tell: A Neural Image Caption Generator.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Show and Tell: A Neural Image Caption Generator

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.259804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a527a13f-90bd-44f5-bb4c-51066d687006 · outbound

This paper cites Williams and David Zipser.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Williams and David Zipser

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.460908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff799bb0-a499-45b0-92ac-706ca3e80c74 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.465513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bfa728-1bcd-478f-9d6e-2811cfbb57c9 · outbound

This paper cites Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:54:07.843322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d65f81b4-967e-404e-8654-878df42752e8 · outbound

This paper cites Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.475975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3cd6475-4543-4c0e-8236-abd437ac145b · outbound

This paper cites Long-CLIP: Unlocking the Long-Text Capability of CLIP.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Long-CLIP: Unlocking the Long-Text Capability of CLIP

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.244519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f718f707-c561-4728-8380-7e35690e5b44 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and ChatBot Arena.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Judging LLM-as-a-Judge with MT-Bench and ChatBot Arena

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:54:08.229072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6f086885-8685-4fc2-b806-57d9071481e0 · outbound

This paper cites TinyLLaVA: A Framework of Small-scale Large Multimodal Models.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning TinyLLaVA: A Framework of Small-scale Large Multimodal Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.489842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e04bb7-6ef2-4bcc-940e-cb9fbbfdbcac · outbound

This paper cites Analyzing and Mitigating Object Hallucination in Large Vision-Language Models.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.495920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09177a3-2dff-408d-b6d8-41e2b961faf9 · outbound

This paper cites write newline.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.500846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ad4be19-2a90-4da5-aed7-b1bedd829d8c · outbound

This paper cites @esa (Ref.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning @esa (Ref

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.506424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9de5f4f-b01c-4a4e-831e-660f9102906f · outbound

This paper cites an unresolved cited work.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T17:54:07.511197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3211a005-83a0-478e-b09a-3f91a3c860a5 · outbound

This paper cites \\ DCI & 7,805 & 10 & 45 & Images from SA-1B with detailed captions of up to 77 tokens, summarized with an LLM from hyper-detailed captions of 1k tokens.

The Devil is in the EOS: Sequence Training for Detailed Image Captioning \\ DCI & 7,805 & 10 & 45 & Images from SA-1B with detailed captions of up to 77 tokens, summarized with an LLM from hyper-detailed captions of 1k tokens

Reference 40

Resolution: malformed identifier; no resolver link, observed 2026-08-15T17:54:07.515977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.