Pith. sign in

Paper Citation Record · LEDGER

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding

As of 17 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2607.24554.

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

pith.paper-citation-record.v1
2607.24554 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T11:50:17.038882Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

52 of 52 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved52
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 41829841-1f6c-4b14-a1a1-d2c998ea02cc · outbound

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

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.795608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.795608Z digest=sha256:fa4543a7ee5ed70f4ed68d573ec5fde844b25691230bdc2c9ada23cb5e9fa823

Observation 3ba4573b-47b4-4b64-aea9-5276a83c8aed · outbound

This paper cites GPT-4 Technical Report.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding GPT-4 Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.801291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.801291Z digest=sha256:aa8692f79a9df1023167b88b1bd317455d2c5a30833ececbbd435e71ec895b1d

Observation 59715cea-d6ec-4368-9e6c-93948870bf95 · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Retrieval-augmented generation for knowledge- intensive nlp tasks,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.807373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.807373Z digest=sha256:e831b73cf9fc50d09f10df081568bbe6e964dbc6236810c5e2241d1f0ee7b9f4

Observation 92687639-6069-42f9-bcac-6985d6d4149a · outbound

This paper cites REALM: Retrieval-augmented language model pre-training,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding REALM: Retrieval-augmented language model pre-training,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.812261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.812261Z digest=sha256:0e512ae4a3c88421c263c416362fe90e31ae552a1c49d1e0cfd87c375413ba68

Observation 5e244521-82db-4030-a6f9-6d450cb971a9 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.816904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.816904Z digest=sha256:4fa2463f787d816900d115a691555face09d2a0c066a856987bd6006a69a63a3

Observation db3aa38a-246b-4b70-bc5f-b7de7189ef98 · outbound

This paper cites Dense passage retrieval for open-domain question answering,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Dense passage retrieval for open-domain question answering,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.821943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.821943Z digest=sha256:f205d8e9a0967dd938993f668e5e43ba1c2636c20d09ab8f12ad0d16a0e3b678

Observation 65338d73-ecc2-4d7e-9b0d-fa3b2d56ed34 · outbound

This paper cites Leveraging passage retrieval with gener- ative models for open domain question answering,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Leveraging passage retrieval with gener- ative models for open domain question answering,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.827420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.827420Z digest=sha256:cd36c1136f48f0bbaf0e15e1d535c8888c5a31d86f198239d26e88e43a8b042a

Observation 8377accc-974b-4f82-85eb-42894bf01566 · outbound

This paper cites Rag-anything: All-in-one rag framework,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Rag-anything: All-in-one rag framework,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.832747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.832747Z digest=sha256:4ecbe61df10c23533087dc63fabd46c376be187f92283bcee05c8d516daf493a

Observation 5c09b5d7-963c-416f-99c1-c874d3b0dc4c · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.837528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.837528Z digest=sha256:1ec4d2417caedfa8027010bb8874cf0dede2f56ca5bf67fe473bb24beeda1f8f

Observation 929ad0b4-5c31-4378-8de2-afcd54952882 · outbound

This paper cites G-Retriever: Retrieval-augmented generation for textual graph understanding and question answering,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding G-Retriever: Retrieval-augmented generation for textual graph understanding and question answering,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.844740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.844740Z digest=sha256:db078e2a6d0f44c28546b31bc2d590de065fe67fe29740e000f1d4231ea873fe

Observation 6040179f-ffba-4a53-b643-2f1dbdadce3b · outbound

This paper cites LayoutLMv3: Pre- training for document ai with unified text and image masking,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding LayoutLMv3: Pre- training for document ai with unified text and image masking,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.849336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.849336Z digest=sha256:1e7bd95dee4a85393131e29d7918d5664dd51536467ed0ae0c0e4a1d77139f94

Observation 016f70e2-b95a-43d6-95a1-6c4d95a3705e · outbound

This paper cites Ocr-free document understanding transformer,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Ocr-free document understanding transformer,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.853632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.853632Z digest=sha256:987c6c29f25729bb0a71f8efeb2d887c8dbaad6001b4995ff6b1b55518b22dd1

Observation ab5fa990-c5ab-4651-8637-775fabdc49ef · outbound

This paper cites Nougat: Neural Optical Understanding for Academic Documents.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Nougat: Neural Optical Understanding for Academic Documents

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.858739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.858739Z digest=sha256:bbcb718dcab936f569cc82ebba1d923a81389c4d0d7819570fbf4a48d153b990

Observation 37cd1b6a-1025-4541-b38f-62df47cab9db · outbound

This paper cites Docvqa: A dataset for vqa on document images,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Docvqa: A dataset for vqa on document images,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.863633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.863633Z digest=sha256:2ace9886d9d01432aff7d90941c1c69b6e854859f2dee750e9831e2589564808

Observation bb62cb33-c922-4c1a-9a69-5dbe25e44e5b · outbound

This paper cites Towards vqa models that can read,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Towards vqa models that can read,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.868784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.868784Z digest=sha256:02e89fcfa70acebe192818ddb95cc3359e915691f9c7f65258ba78c43660a4ea

Observation a71fd1b7-d9cc-444f-beba-2aa666c20168 · outbound

This paper cites Visual instruction tuning,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Visual instruction tuning,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.873298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.873298Z digest=sha256:2c0b72bf6c63501cbd2be84098991fa15cfce7ef7df5f7d9d7013b3d176afbbd

Observation 34d858f3-609b-47a7-92fc-5c55517ae89a · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.877480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.877480Z digest=sha256:0ef5a84f2f84a98f926f68b87d3b20157b6ab418ebc343b133897b6e7591409a

Observation 8499f592-9750-43be-867c-ab0b790d6756 · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Flamingo: a visual language model for few-shot learning,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.881979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.881979Z digest=sha256:450a02733468f50822db76df07310faf8d415c5bbdc7528ef573804c7f6bb983

Observation 1000e979-cf55-475b-9a02-8e9d787dcd6a · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruc- tion tuning,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Instructblip: Towards general-purpose vision-language models with instruc- tion tuning,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.886600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.886600Z digest=sha256:1a65224dee23443258d32fbfb32f7b6c30b2764cbb33e4903d50dc62912cf7d7

Observation d74ca9f0-2d69-435f-8060-248fec30caf7 · outbound

This paper cites Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.891078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.891078Z digest=sha256:26348c50ce1fe795783932e65ae5eaa5e36c6d6635a2678805e81dffa0a6b965

Observation 9c96694d-d056-4bea-9113-5e7633cf9f7a · outbound

This paper cites Mitigating object hallucinations in large vision-language mod- els through visual contrastive decoding,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Mitigating object hallucinations in large vision-language mod- els through visual contrastive decoding,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.896317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.896317Z digest=sha256:dbb549e7865aee07fea02b28e87277e572d97163736f418f997c025b31b1ce13

Observation 9a1e40bb-c73b-41f5-a1cf-6e23e423581f · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Woodpecker: Hallucination correction for multimodal large language models,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.901016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.901016Z digest=sha256:f2e20fd7718829d8296c866af8b0410cae16bb1e13e7ecd76d124355ad884b49

Observation 5002b4f4-1704-438a-b5cd-b637d5b38468 · outbound

This paper cites Hallusionbench: An advanced diagnostic suite for entangled language halluci- nation and visual illusion in large vision-language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Hallusionbench: An advanced diagnostic suite for entangled language halluci- nation and visual illusion in large vision-language models,

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.906124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.906124Z digest=sha256:0fe3b6ade6db7cfd5546c56d627be1d404ba68b78e0bb6b29753bcaa96a0849b

Observation 0e831a6f-5d79-4c84-8152-ffde74c09792 · outbound

This paper cites Evaluating object hallucination in large vision-language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Evaluating object hallucination in large vision-language models,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.911208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.911208Z digest=sha256:7a8a7c9675596e66e9af36d30892f0083345b6fba3126f561fc98b3b88552294

Observation b708b922-a340-4b59-91b1-5e9242f1636c · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.915847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.915847Z digest=sha256:ed365d2bd24c4c80734633b2d2038f1a0b2a84a18ad466e8064cb2185d026d07

Observation 8210469d-d5a2-4bec-86ed-8c6713159bb6 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.919876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.919876Z digest=sha256:5e1d8229326325290fad2e8404fa1296915d2911723b45f4175538e9010d3827

Observation 86920734-58a7-444a-981d-c75646e06780 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Flashattention: Fast and memory-efficient exact attention with io-awareness,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.924569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.924569Z digest=sha256:e639a600d0a9f4531b4696112f4dd49b3f747f661d3fb8960b2debf7d7365a88

Observation 130e3855-dc80-4f7f-a9d7-242826f6d2bf · outbound

This paper cites Vision trans- formers need registers,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Vision trans- formers need registers,

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.928529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.928529Z digest=sha256:72a311f0a82ded3f2e1b34b8049fc9bca3b762d6ae1423a023682c1251c46731

Observation 219bf8f2-f9c6-4904-9f19-09e36d4dcd62 · outbound

This paper cites Efficient streaming language models with attention sinks,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Efficient streaming language models with attention sinks,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.932442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.932442Z digest=sha256:d2f05bd4073308f9eceda734ddb2c4e881ee03d98c28adf2cb42f07bc62c3701

Observation 14e89e45-5f30-4b1a-b4a0-638c9cb50e0b · outbound

This paper cites LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.936655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.936655Z digest=sha256:91e70921c425b84a2b83dee74b2e3040d3335e9f7b63bbc4bfb13d9442bef3b4

Observation da4ab357-7e51-49fb-8683-076a8cb7ed62 · outbound

This paper cites H 2O: Heavy- hitter oracle for efficient generative inference of large language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding H 2O: Heavy- hitter oracle for efficient generative inference of large language models,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.940891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.940891Z digest=sha256:d5d7756f0474de0bcacb386843e4c489808d69b2777bd9d0786906db4184e083

Observation 43b563f1-2cf4-4cc3-932d-2c5f07c518be · outbound

This paper cites Colpali: Efficient document retrieval with vision language models,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Colpali: Efficient document retrieval with vision language models,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.945194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.945194Z digest=sha256:21f46b66bcc96ef2afcdc801092aeb3802c1479a824660242234270df21ef123

Observation 5550d6fc-fb7c-40e6-80a9-6cfac09e2742 · outbound

This paper cites MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.949425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.949425Z digest=sha256:18581841c127a46f7e20d76e014f9ae18bc758e38d81d061da3171262e6e54a1

Observation a516b7d0-04b3-4d08-b298-b5ff3c44d164 · outbound

This paper cites VisRAG: Vision-based retrieval-augmented generation on multi-modality documents,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding VisRAG: Vision-based retrieval-augmented generation on multi-modality documents,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.953929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.953929Z digest=sha256:8bd522a64a3ab5fdc1808a2971dc2e3adf21e25764b22dab1259faed6d2603a1

Observation 34bb4fae-e9b9-4051-b9bd-b1dec10dd87c · outbound

This paper cites MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.958407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.958407Z digest=sha256:cedfee0df3fc352f61e635c2ffa367e4acf1c6f3de0390ac6e1b59af20c1c9bf

Observation c45b05a9-1a2a-48f9-a2d2-f1467c838980 · outbound

This paper cites Image cropping with spatial-aware feature and rank consistency,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Image cropping with spatial-aware feature and rank consistency,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.963066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.963066Z digest=sha256:3227ee6cd30b75d61e0d8de30a8ff51d1e69cdd27ec567a0510d547fc3d37cdb

Observation 232506d8-055a-4bd7-9857-27d92765e705 · outbound

This paper cites Reliable and efficient image cropping: A grid anchor based approach,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Reliable and efficient image cropping: A grid anchor based approach,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.967383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.967383Z digest=sha256:a0614a441e6b781ff98d1a43a479c726a6f671539cd6c54541158400846ca44f

Observation 867d78a0-9d82-40bd-8d18-1e2c2e415ea4 · outbound

This paper cites Cropper: Vision-language model for image cropping through in-context learning,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Cropper: Vision-language model for image cropping through in-context learning,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.971375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.971375Z digest=sha256:70560e03a8e4dd9577edc94a880fe01f3d465754e3c224f5bcb569e3f897ff7a

Observation dd04d064-6e10-4f74-8517-0dc5168f0875 · outbound

This paper cites mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Reference 39

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.975786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.975786Z digest=sha256:3de7394755a03195f7493831b1abd3cc820b690dc1171cc68c6033b8c4f1a496

Observation 7471fcc5-67e8-4014-8bb6-3a55551cfc4a · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.980324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.980324Z digest=sha256:8575bf4a3ffdb6eaa589a6d3d45a1c7f05691d3f82441e137a57e30a2b935f84

Observation fd152c35-110d-4982-b441-20419457569e · outbound

This paper cites AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.984679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.984679Z digest=sha256:0de0d5e4c01192eeb0466213da99683332eb6f27495f306fa99d769d15b1a666

Observation 1ab9c76e-b4ce-42b2-9040-fba8b3d44a12 · outbound

This paper cites Spiqa: A dataset for multimodal question answering on scientific papers,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Spiqa: A dataset for multimodal question answering on scientific papers,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.989303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.989303Z digest=sha256:eadf8a839c4b503e3a0835f8669c0796046e88cf11c7b3a3290cdfa78ea528e4

Observation ead5d471-58ad-4e3c-9aa5-d5156bedca8f · outbound

This paper cites Deformable detr: Deformable transformers for end-to-end object detection,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Deformable detr: Deformable transformers for end-to-end object detection,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.994579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.994579Z digest=sha256:e6fd7872b38790ed2f6cb6868f852faa40db29d0ac7fde900709431bdae17394

Observation 262f7719-6c94-42fd-8518-58518700aaf1 · outbound

This paper cites Chartqa: A benchmark for question answering about charts with visual and logical reasoning,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Chartqa: A benchmark for question answering about charts with visual and logical reasoning,

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:16.998840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:16.998840Z digest=sha256:6b61bd0873fa7845c6fb2768c726009faebe5dc43a76b8bc9c28f03d925e17ee

Observation ad5d0b5a-1a43-4196-84e0-ac37f230d527 · outbound

This paper cites Deplot: One-shot visual language reasoning by plot-to-table translation,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Deplot: One-shot visual language reasoning by plot-to-table translation,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.003727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.003727Z digest=sha256:111023144f6c37e16f2f0859942aae07641d8a1bea7096dd89df730d3a1d7b4f

Observation 2bc540e9-230a-4de2-b5a0-ef3973cbac23 · outbound

This paper cites Plotqa: Reasoning over scientific plots,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Plotqa: Reasoning over scientific plots,

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.008938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.008938Z digest=sha256:6be09f1a67a529e82868b6c690e63f39467631f659c795bf3b9b9e093f951d0b

Observation 92360df7-3e07-4e1d-8c0f-c82c25fe49cf · outbound

This paper cites Slidevqa: A dataset for document visual question an- swering on multiple images,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Slidevqa: A dataset for document visual question an- swering on multiple images,

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.013678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.013678Z digest=sha256:5f19e76679ee600faec661516719583022e242309aef9f281a51ffa802d02eac

Observation 4003b05b-452d-451e-8e25-d8e26bb03c97 · outbound

This paper cites UDA: A benchmark suite for retrieval augmented generation in real-world document analysis,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding UDA: A benchmark suite for retrieval augmented generation in real-world document analysis,

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.018502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.018502Z digest=sha256:670b05df0b0702c2ee06ea9a7bfe50e69e50838bfdaa1b79a835bb974eb5dc7c

Observation 7fd32828-45bb-4cb7-bd97-fb7755a5d14e · outbound

This paper cites TabFact: A large-scale dataset for table-based fact verification,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding TabFact: A large-scale dataset for table-based fact verification,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.022999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.022999Z digest=sha256:98bc7d2326cc196653f7ea49694036a958f4828360e698e8b1969ccbf4221684

Observation 6fb2e673-797b-42a2-82cc-288015b77ae7 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.027871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.027871Z digest=sha256:a55362b619f584366d8837c8d001c5f829da34fab79209f88d9785a47372128f

Observation 2ea06288-f13a-47b9-88be-c7b61a182201 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chat- bot Arena,.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding Judging LLM-as-a-Judge with MT-Bench and Chat- bot Arena,

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.033929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.033929Z digest=sha256:60b8a4ceb5a38b7880e8e856290c2dc75f13c08833f76fc484422910e2cadca0

Observation 9f7fdeec-b2ad-4ee7-9e22-d8be414ddd71 · outbound

This paper cites G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment.

DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

Reference 52

Resolution
unresolved
no resolver link, observed 2026-07-31T11:50:17.038882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:50:17.038882Z digest=sha256:a45ad3ef6704ca0a0f8279bcf06f9e805e875f63875edc95073e902edb6b3764

Pith citing papers

No inbound Pith citation observations are available.