Paper Citation Record · LEDGER

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

As of 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 7 inbound Pith citation observations for arXiv:2504.19754.

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

pith.paper-citation-record.v1
2504.19754 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:46:52.814255Z

measured 27 of 27 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 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:19:44.353255Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-11T02:27:48.576436Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy2
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 469de592-fa2a-458f-84ac-7f089ac8a6bf · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.674270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 220ccdbf-e679-4e03-bee6-49914ee8050f · outbound

This paper cites MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.681575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cc666f-6392-4952-9869-bedaf272d5d2 · outbound

This paper cites an unresolved cited work.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.686890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3657acda-e92c-4aae-9616-c33d50a2efed · outbound

This paper cites M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.694462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aac5afd-555a-4fb0-8bce-9cdf6d53cb79 · outbound

This paper cites In: Forty- first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation In: Forty- first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:46:53.246576Z

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 b4f1e814-4247-44b5-a51e-56d5d9205f6a · outbound

This paper cites A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.719111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffedbd54-830e-4ef4-b9e9-1882695432eb · outbound

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

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.726866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420706ad-2645-4db7-8f09-d58caa73a26a · outbound

This paper cites A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.732860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e274da5-4dd9-4d23-8b4a-9178cea1a75c · outbound

This paper cites Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.739040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2120dff-d075-443a-b1ed-a70645d4de32 · outbound

This paper cites Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.748172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a03475c-fee1-4f08-aa2a-df865e0c4995 · outbound

This paper cites Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.753910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0274ead1-f2cf-479f-8b7f-6ca1d28ef56f · outbound

This paper cites an unresolved cited work.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:46:53.225744Z

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 89c82215-9396-4677-bac9-dfa1750dc747 · outbound

This paper cites Dense Passage Retrieval for Open-Domain Question Answering.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Dense Passage Retrieval for Open-Domain Question Answering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.765536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 645d124f-1114-4333-a033-142cb2951e6a · outbound

This paper cites Text Segmentation as a Supervised Learning Task.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Text Segmentation as a Supervised Learning Task

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.772711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1209d2d-2b10-4576-bc0f-ffa95272ec0c · outbound

This paper cites In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:46:53.200104Z

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 09c6b4f7-5154-4c94-a858-f854f72d857b · outbound

This paper cites Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.784159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f351814-4b6f-40a1-b115-cc77bb361ae6 · outbound

This paper cites Neurocomputing 548, 126356 (2023).

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Neurocomputing 548, 126356 (2023)

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.789920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0bfeea0-a425-4f89-92e8-3f506db93e93 · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation MTEB: Massive Text Embedding Benchmark

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.795899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a23d3a8e-55c6-4fed-b61d-a38552b0be70 · outbound

This paper cites Foundations and Trends in Information Retrieval3, 333–389 (01 2009).

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation Foundations and Trends in Information Retrieval3, 333–389 (01 2009)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.803949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8c3c617-a5e9-4024-8633-a2709e7cc3e8 · outbound

This paper cites jina-embeddings-v3: Multilingual Embeddings With Task LoRA.

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:52.814255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e61fc616-9851-4fb2-9a1b-8bc2aef2168a · inbound

KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation cites this paper.

KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T20:19:44.353255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a105d9ae-7f0b-4ed7-9853-587702869774 · inbound

Benchmarking Information Retrieval Models on Complex Retrieval Tasks cites this paper.

Benchmarking Information Retrieval Models on Complex Retrieval Tasks Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T22:37:58.191041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf52d711-e999-41cf-9586-fab706bb5ea5 · inbound

Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation cites this paper.

Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:21:09.767391Z

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 2f7192ce-d728-4e14-93f2-169cff638bc0 · inbound

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding cites this paper.

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:31:25.294988Z

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 3dab71fa-5240-48cc-9a7d-177850649c54 · inbound

Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents cites this paper.

Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:21:10.730583Z

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 11a9dd4a-3389-4e72-b1a6-ea78fed824b3 · inbound

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents cites this paper.

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-11T02:27:48.593482Z

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 2932bfd4-8075-43a4-8e21-335885d783bd · inbound

Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System cites this paper.

Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T18:01:58.815464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.