Paper Citation Record · LEDGER

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment

As of 10 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 2 inbound Pith citation observations for arXiv:2501.14296.

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

pith.paper-citation-record.v1
2501.14296 v1

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T15:19:01.309104Z

measured 13 of 13 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:31:00.001334Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T14:43:58.335104Z

Reference resolution

11 of 11 outbound references displayed

verified exact0
verified fuzzy2
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2dd6df6-9cac-4078-b18b-4d7f2b5391d4 · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.508069Z

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 bea5a6c1-dcde-4fb9-a69c-95fcad2426e3 · outbound

This paper cites Voorhees, and Ian Soboroff.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Voorhees, and Ian Soboroff

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T15:19:01.492445Z

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 fad2b0a8-4ccc-4e25-9597-09e6f0c09ad9 · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.476177Z

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 619723c5-648e-4c5f-99e6-f73ae0c4c7eb · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.448899Z

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 fc1da27e-3d1a-4abf-a072-d8ed35f8fe4a · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.434673Z

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 bf399a4e-3747-462e-ac6e-ac93afe38f9d · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.406121Z

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 d7d6b61f-4c44-47e7-b4e6-b96a6a891013 · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.391508Z

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 fa85362c-fafb-47bd-a761-5c992578f605 · outbound

This paper cites UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T15:19:01.298408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 052c5493-1504-4ca9-b7ab-61b3037d0773 · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T15:19:01.304353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c977d79-12de-4c87-a3ab-368fb4686a14 · outbound

This paper cites Shane Culpepper, Falk Scholer, and Paul Thomas.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Shane Culpepper, Falk Scholer, and Paul Thomas

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T15:19:01.365684Z

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 16bde970-20a3-4ad1-8f6f-418d7b102371 · outbound

This paper cites an unresolved cited work.

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:19:01.420325Z

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 5a07de35-388b-415a-a0f9-79f19c4ac1ec · inbound

Large Language Models in the Task of Automatic Validation of Text Classifier Predictions cites this paper.

Large Language Models in the Task of Automatic Validation of Text Classifier Predictions Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:00.001334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230f0533-fcec-4b05-ba69-87b8accca1b6 · inbound

Synthetic Data Generation for Phrase Break Prediction with Large Language Model cites this paper.

Synthetic Data Generation for Phrase Break Prediction with Large Language Model Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:43:58.338469Z

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.