Pith. sign in

Paper Citation Record · LEDGER

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding

As of 6 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 1 inbound Pith citation observation for arXiv:2604.22335.

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

pith.paper-citation-record.v1
2604.22335 v1

Coverage vector

measured 8 of 8 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T11:58:36.326809Z

measured 9 of 9 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T02:01:14.533941Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T23:01:15.317143Z

Reference resolution

8 of 8 outbound references displayed

  • verified exact2
  • verified fuzzy3
  • unresolved0
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ef863d8d-af3c-4ac7-8685-b5cdc9314501 · outbound

This paper cites A Semantic Invariant Robust Watermark for Large Language Models.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding A Semantic Invariant Robust Watermark for Large Language Models

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T19:26:09.035196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:051407927e848c8fafd905e74939b23906bdbf1d3f1134eed28cc0be5aee6f5a

Observation 2bbb8105-898e-4c2e-80f6-019dd37271c0 · outbound

This paper cites FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows".

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:26:09.030214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:00a0c3d726470a64ada9f7aaa1e67c9bebcc60713ecf88ede9ed3f0fd02cbda5

Observation 93bd03ca-295c-48ec-bfc7-cf08a0afd7c3 · outbound

This paper cites Shashi Narayan, Shay B.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding Shashi Narayan, Shay B

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:47:49.255807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:03616c17080e889d0ea45f790528ac967ba17bb86f3547c7e49669139516033b

Observation 40bcf780-cbc1-452e-9d1c-e2ecd9d95824 · outbound

This paper cites InProceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 1797–1807, Brussels, Bel- gium.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding InProceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 1797–1807, Brussels, Bel- gium

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:47:49.252384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:cbbb8aa9bbb3f8601e5e85384b1e90f25eef894acb5b210173775d61339ffcc5

Observation 2f77a6d7-c3ac-470d-b53b-3eb316df9519 · outbound

This paper cites Entropy-Based Decoding for Retrieval-Augmented Large Language Models.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding Entropy-Based Decoding for Retrieval-Augmented Large Language Models

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:26:09.017507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:a6fe7c63149849f08b6871b398a92b8d8000d3c0c316d42b397374df7b3f12b0

Observation c8633b02-a421-436d-9a69-1f1c7e99610a · outbound

This paper cites InProceedings of the 55th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073– 1083, Vancouver, Canada.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding InProceedings of the 55th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073– 1083, Vancouver, Canada

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:47:49.247862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:df3c9edb502062ff9d1137365513d4e1a6344041546bcec8c486e5236d82440f

Observation dbaca172-215d-4fe4-9d3c-f7cb034c823d · outbound

This paper cites A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

Reference 7

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T19:15:13.402482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:2b199b5937136de0b675590d901c6e6de4918fcf93a5d05edc86e7de7c92a9cb

Observation eb24bd27-3deb-44fa-bd7a-1d62965856d2 · outbound

This paper cites Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering.

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering

Reference 8

Resolution
malformed identifier
arxiv_id, observed 2026-05-11T19:26:09.026153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T11:58:36.326809Z digest=sha256:f639b1012ec950240f443effff1e2a146ca6baee68ef59cc6878ecb0638a2c5b

Pith citing papers

Observation cf0ea998-20b4-44e5-abb8-b6b16f77ab27 · inbound

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models cites this paper.

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding

Reference 58

Resolution
verified exact
local_arxiv, observed 2026-05-11T23:01:15.320226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-08T02:01:14.533941Z digest=sha256:c98c5c582d823e29c4502631cb487514cf3fa4bad153658271efc1f8c9519c0e