Paper Citation Record · LEDGER

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference

As of 10 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2605.09990.

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

pith.paper-citation-record.v1
2605.09990 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:11:02.387702Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T02:10:49.607668Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact17
verified fuzzy4
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 05b7628d-aeaf-40b0-9b8d-53368d3c46b3 · outbound

This paper cites Deduplicating Training Data Makes Language Models Better.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Deduplicating Training Data Makes Language Models Better

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.944427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf8d9cd0-d923-4fd0-a693-82da1f9adc80 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Quantifying Memorization Across Neural Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:04:59.782633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bf8483c-ef73-41de-ad49-1a4e4bb114d0 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Scalable Extraction of Training Data from (Production) Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:00:47.082021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36ff924d-c023-47c7-98c4-516d81ef92a6 · outbound

This paper cites Feder Cooper, Sanmi Koyejo, and Percy Liang.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Feder Cooper, Sanmi Koyejo, and Percy Liang

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.864899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 54243831-e618-4831-8675-9e562b8cd817 · outbound

This paper cites The Mosaic Memory of Large Language Models.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference The Mosaic Memory of Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.983122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd6de052-7f4c-4ef7-9b8c-adbd34715f51 · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.424487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 698e703d-87ac-4ced-b0ef-f07ba77f9255 · outbound

This paper cites Khan et al.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Khan et al

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.854624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 98168528-4398-4209-bf99-3e97ed42533e · outbound

This paper cites SemDeDup: Data-efficient learning at web-scale through semantic deduplication.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference SemDeDup: Data-efficient learning at web-scale through semantic deduplication

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:43:31.136179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3865ca08-8af6-4f3c-afd7-a546f6bfdd0c · outbound

This paper cites D4: Improving LLM Pretraining via Document De-Duplication and Diversification.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference D4: Improving LLM Pretraining via Document De-Duplication and Diversification

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:29.028876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d8aedb57-aa1a-4d2a-9539-8cfb0a331c71 · outbound

This paper cites SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.952124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation acabebab-b63c-412e-8cb7-a301caccd2be · outbound

This paper cites Refrag: Rethinking rag based decoding.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Refrag: Rethinking rag based decoding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:29.009877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3eb4c956-f3c9-4d6a-884d-419ff7b96a9e · outbound

This paper cites ContextPilot: Fast Long-Context Inference via Context Reuse.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference ContextPilot: Fast Long-Context Inference via Context Reuse

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:31:28.883854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 127ab671-202c-4e16-baa8-2ff4da1b84a9 · outbound

This paper cites Rethinking soft compression in retrieval-augmented generation: A query- conditioned selector perspective.arXiv preprint arXiv:2602.15856, 2026.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Rethinking soft compression in retrieval-augmented generation: A query- conditioned selector perspective.arXiv preprint arXiv:2602.15856, 2026

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.845920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 648fcaa2-331e-4c2c-8505-73091bc99a59 · outbound

This paper cites Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:31:28.994381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 53baad14-d3b3-43ca-bc7e-b2b3b40d38da · outbound

This paper cites Udayashankar, A.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Udayashankar, A

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.897404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5dee1db0-a127-4638-91cc-5fd95b8faad8 · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.450731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff53a8fc-598b-46f9-ba50-a1721848ede5 · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.446820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 29966568-3a1f-4535-bf39-7f2d15b81956 · outbound

This paper cites Don ’t Maintain Twice, It’s Alright: Merged Metadata Management in Deduplication File System with GogetaFS.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Don ’t Maintain Twice, It’s Alright: Merged Metadata Management in Deduplication File System with GogetaFS

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:16:41.428007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 38160899-be6e-45a8-b6c6-6f7b269ef532 · outbound

This paper cites Chursin, L.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Chursin, L

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.962837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5864501d-291d-49f2-a1d4-30ae0ff087c7 · outbound

This paper cites Zipllm: Efficient llm storage via model-aware synergistic data deduplication and compression.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Zipllm: Efficient llm storage via model-aware synergistic data deduplication and compression

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:28.875586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 88948b69-40a1-4e39-b6a1-85ad12031404 · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.436178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5bc0c6b3-9ae2-4f38-9bb1-8481af501f59 · outbound

This paper cites Bronson et al.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Bronson et al

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:16:41.439485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ab4571b-9b95-475b-92c8-414a1875d77a · outbound

This paper cites Verbitski et al.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Verbitski et al

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:16:41.461220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dcee8636-a82a-4a06-9a07-ca1ba335017f · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.458163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 80c1db59-57f5-4e61-9f7f-c9122038db97 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T04:36:45.776658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de158180-de0c-478f-bc32-b98aaae5bf2a · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.432623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2b0fe67f-2b90-46fe-bec4-c37757e30173 · outbound

This paper cites an unresolved cited work.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:16:41.454047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6e185ab-cd6e-44ec-8a95-a3f5e27e8ab0 · outbound

This paper cites unique={len(unique)} duplicate={total - len(unique)}.

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference unique={len(unique)} duplicate={total - len(unique)}

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:16:41.443209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 0d19c8ef-1365-4605-88ae-b3ed6e986b9f · inbound

Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel cites this paper.

Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T02:10:49.607668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.