Paper Citation Record · LEDGER

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

As of 6 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 2 inbound Pith citation observations for arXiv:2604.16940.

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

pith.paper-citation-record.v1
2604.16940 v1

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T07:28:14.002938Z

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T05:56:09.398837Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-22T06:01:09.210696Z

Reference resolution

6 of 6 outbound references displayed

verified exact1
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c3d00226-139d-42b9-9f76-21a06c374d22 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation Evaluating Large Language Models Trained on Code

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T07:52:13.998332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 51f2bde2-4d46-4879-8a4e-5fe43261d705 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T20:25:34.870358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7f508ac2-4c8f-4f82-aabc-dcb6a97e768c · outbound

This paper cites InProceedings of the Inter- national Conference on Learning Representations (ICLR).

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation InProceedings of the Inter- national Conference on Learning Representations (ICLR)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T13:35:11.961878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7a936d9e-3180-4a78-b341-5b2e09896bdd · outbound

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

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T07:52:13.996108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation be4b083e-48eb-4433-8e2f-415872f08e78 · outbound

This paper cites Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, and Guanhua Chen.

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, and Guanhua Chen

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T13:35:11.958253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8838d0ae-e171-464f-8210-e3b164ac0528 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation Instruction-Following Evaluation for Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-10T07:52:13.991151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation e45f90e9-7ef3-4952-82cc-01e289eea5b4 · inbound

Dynamic Model Merging Made Slim cites this paper.

Dynamic Model Merging Made Slim D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-20T15:18:25.361634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5f0efdcb-cd26-496b-95a3-525fc5c7b614 · inbound

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks cites this paper.

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T06:01:09.213426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.