Paper Citation Record · LEDGER

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring

As of 22 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2606.11700.

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

pith.paper-citation-record.v1
2606.11700 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T08:28:14.637197Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

37 of 37 outbound references displayed

verified exact1
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9c394a53-06a9-455d-b2a2-4d588c41182d · outbound

This paper cites Hyperrag: Enhancing quality-efficiency tradeoffs in retrieval-augmented generation with reranker kv-cache reuse, 2025.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Hyperrag: Enhancing quality-efficiency tradeoffs in retrieval-augmented generation with reranker kv-cache reuse, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb349981-357d-4d85-aeef-fc445ca136ce · outbound

This paper cites Peters, and Arman Cohan.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Peters, and Arman Cohan

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e63875-413a-420c-b64f-65ea8379ed23 · outbound

This paper cites Attention in large language models yields efficient zero-shot re-rankers.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Attention in large language models yields efficient zero-shot re-rankers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baed1cff-ad9d-446c-a92c-bc1ec0e01cd6 · outbound

This paper cites Deepseek-v3.2-exp: Boosting long-context efficiency with deepseek sparse attention, 2025.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Deepseek-v3.2-exp: Boosting long-context efficiency with deepseek sparse attention, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4182bc33-7acb-4a70-8cb0-c8f6619aab4c · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Deepseek-v4: Towards highly efficient million-token context intelligence, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f26a5201-4ddb-4d0a-9dea-b1bb725a4d71 · outbound

This paper cites Reranking with compressed document representation, 2025.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Reranking with compressed document representation, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c95d6d35-0a83-4a5e-b973-201b6d84a1c9 · outbound

This paper cites minireranker: Efficient multimodal reranking through visual cache reuse and interaction sparsity, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring minireranker: Efficient multimodal reranking through visual cache reuse and interaction sparsity, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf1e490-f436-4276-9dae-89e654ec8268 · outbound

This paper cites an unresolved cited work.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f29792c-fe48-46fa-8290-3e514eda3c2b · outbound

This paper cites an unresolved cited work.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a761262-7854-419e-b4e3-46198bf851f4 · outbound

This paper cites MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-03T13:08:08.705595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bf7452dd-a363-4546-ae0b-c808e6532631 · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d61fe9-e097-45a4-b0ba-209c9b9900d7 · outbound

This paper cites Efficient long-document reranking via block-level embeddings and top-k interaction refinement, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Efficient long-document reranking via block-level embeddings and top-k interaction refinement, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f58049c5-1db7-4097-ae57-3cacef1d30e2 · outbound

This paper cites Leveraging passage embeddings for efficient listwise reranking with large language models.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Leveraging passage embeddings for efficient listwise reranking with large language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60dbdb9d-ff8d-44ed-b7c8-509066102468 · outbound

This paper cites Rethinking reasoning in document ranking: Why chain-of-thought falls short.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Rethinking reasoning in document ranking: Why chain-of-thought falls short

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9ae6e0-83c3-4e3c-8b58-c66fcdb8d437 · outbound

This paper cites Tools are under- documented: Simple document expansion boosts tool retrieval.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Tools are under- documented: Simple document expansion boosts tool retrieval

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3e8ec42-8388-42a5-9bd9-8a0a6caa6166 · outbound

This paper cites Beyond global similarity: Multi-conditional retrieval for fine-grained cross-modal understanding.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Beyond global similarity: Multi-conditional retrieval for fine-grained cross-modal understanding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef1f4d5-b2b8-4d93-927a-eb621c302bbc · outbound

This paper cites MultiConIR: Towards multi-condition information retrieval.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring MultiConIR: Towards multi-condition information retrieval

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5d0720-e746-43fc-a466-daf980772754 · outbound

This paper cites Fine-tuning llama for multi-stage text retrieval.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Fine-tuning llama for multi-stage text retrieval

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c453ad43-1c48-47a0-8e08-0e77446a9984 · outbound

This paper cites Multi-stage document ranking with bert, 2019.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Multi-stage document ranking with bert, 2019

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aa8a126-14eb-4873-95b8-d58396da3643 · outbound

This paper cites Document ranking with a pretrained sequence-to-sequence model.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Document ranking with a pretrained sequence-to-sequence model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fe24b82-8b41-4e92-a4a6-29950b28f200 · outbound

This paper cites Rankvicuna: Zero-shot listwise document reranking with open-source large language models, 2023.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Rankvicuna: Zero-shot listwise document reranking with open-source large language models, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d00969-be2d-4f00-b95b-d4827c269b30 · outbound

This paper cites Rankzephyr: Effective and robust zero-shot listwise reranking is a breeze!, 2023.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Rankzephyr: Effective and robust zero-shot listwise reranking is a breeze!, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 677536d7-25f5-46d4-8678-42d81a8499c9 · outbound

This paper cites Large language models are effective text rankers with pairwise ranking prompting.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Large language models are effective text rankers with pairwise ranking prompting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de562e6a-c9bb-4e3a-bab5-a919b53f04b6 · outbound

This paper cites First: Faster improved listwise reranking with single token decoding.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring First: Faster improved listwise reranking with single token decoding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d087a6-8d4f-48f2-928d-2071075f01b7 · outbound

This paper cites Rankllm: A python package for reranking with llms.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Rankllm: A python package for reranking with llms

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e5d2d5-6158-4507-89c5-d9c79be80d28 · outbound

This paper cites Is chatgpt good at search? investigating large language models as re-ranking agents.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Is chatgpt good at search? investigating large language models as re-ranking agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1e1fd4-6e58-4277-aa1d-bfdfe5f49890 · outbound

This paper cites Is chatgpt good at search? investigating large language models as re-ranking agents, 2024.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Is chatgpt good at search? investigating large language models as re-ranking agents, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da6c47a-00a0-430c-896a-436118afa0a4 · outbound

This paper cites BEIR: A het- erogeneous benchmark for zero-shot evaluation of information retrieval models.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring BEIR: A het- erogeneous benchmark for zero-shot evaluation of information retrieval models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d896ff8-9417-475f-964f-984ed98b7177 · outbound

This paper cites Contrastive retrieval heads improve attention-based re-ranking, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Contrastive retrieval heads improve attention-based re-ranking, 2026

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42802f95-9134-4fc0-bff2-047fb742b4b9 · outbound

This paper cites Headrank: Decoding-free passage reranking via preference-aligned attention heads, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Headrank: Decoding-free passage reranking via preference-aligned attention heads, 2026

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f28849b4-6e9e-4dc3-97a8-0e6aa54407be · outbound

This paper cites When should queries be decomposed? a stage-aware study of query decomposition for multi-condition retrieval, 2026.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring When should queries be decomposed? a stage-aware study of query decomposition for multi-condition retrieval, 2026

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006e55c3-0e9a-4e84-8a3a-7afffd5e283c · outbound

This paper cites Big bird: Transformers for longer sequences.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Big bird: Transformers for longer sequences

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 638d27f1-1571-40db-87bc-11e2fa6ef58f · outbound

This paper cites Query-focused retrieval heads improve long-context reasoning and re-ranking.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Query-focused retrieval heads improve long-context reasoning and re-ranking

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75a675e5-7b63-4c92-9b97-f6d26960dc84 · outbound

This paper cites Compress-then-rank: Faster and better listwise reranking with large language models via ranking-aware passage compression.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Compress-then-rank: Faster and better listwise reranking with large language models via ranking-aware passage compression

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77930a8-8b95-4402-a0fc-9b9e2d1ee1cb · outbound

This paper cites Lon- granker: Efficient one-pass document reranking with long-context large language models.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring Lon- granker: Efficient one-pass document reranking with long-context large language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83630892-db68-41a4-8cc5-b2e67619772a · outbound

This paper cites A setwise approach for effective and highly efficient zero-shot ranking with large language models.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring A setwise approach for effective and highly efficient zero-shot ranking with large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cb3dd8-3c38-4678-b2c6-5f8507109be5 · outbound

This paper cites [n] {passage_n} Search Query: {query}.

CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring [n] {passage_n} Search Query: {query}

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-27T08:28:14.637197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.