Paper Citation Record · LEDGER

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals

As of 7 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2509.08809.

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

pith.paper-citation-record.v1
2509.08809 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T20:11:41.723677Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

21 of 21 outbound references displayed

verified exact0
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1155b71-e107-4bbe-aeae-b27a94747926 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.593705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 780f3e7d-73e0-4609-81b2-53a1f4c6ece5 · outbound

This paper cites Self-teaching prompting for multi-intent learning with limited super- vision.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Self-teaching prompting for multi-intent learning with limited super- vision

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.606910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbd2193e-118d-4d9c-bd11-fc22c1d5cc00 · outbound

This paper cites An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.630126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec452bde-1b91-4f30-835a-199a972eb0e2 · outbound

This paper cites Large Language Model Guided Tree-of-Thought.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Large Language Model Guided Tree-of-Thought

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.647592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92527c59-d016-460c-89fa-24f1b07f8594 · outbound

This paper cites Large Language Models for Data Annotation and Synthesis: A Survey.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Large Language Models for Data Annotation and Synthesis: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.653118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b125de1-3aa7-49cb-8222-c159da1a5b8f · outbound

This paper cites CodecLM: Aligning Language Models with Tailored Synthetic Data.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals CodecLM: Aligning Language Models with Tailored Synthetic Data

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.660463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f8d1606-cbe6-497b-9bbe-dbc658520440 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Finetuned Language Models Are Zero-Shot Learners

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.668846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf3db79-79cd-464d-983f-d6e95b491a94 · outbound

This paper cites Unigen: A unified framework for textual dataset generation using large language models.arXiv preprint arXiv:2406.18966,.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Unigen: A unified framework for textual dataset generation using large language models.arXiv preprint arXiv:2406.18966,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.676658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e045291-eb2a-472f-b5bc-c7a70f28a214 · outbound

This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.683557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 338a3504-808b-4418-8baf-c4d8a489ba21 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals ReAct: Synergizing Reasoning and Acting in Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.691968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e50ffc-9452-48bb-ac5d-c14f7fac065b · outbound

This paper cites ZeroGen: Efficient Zero-shot Learning via Dataset Generation.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals ZeroGen: Efficient Zero-shot Learning via Dataset Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.698533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07457aea-99d2-4fe8-a7a1-b60ed49e0470 · outbound

This paper cites Clusterllm: Large language models as a guide for text clustering.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Clusterllm: Large language models as a guide for text clustering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.711658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ead15a-d86e-4033-a881-23c70738845c · outbound

This paper cites Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.717627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c32b9ed-be89-420c-b367-3de21fab166e · outbound

This paper cites yi denotes the LLM annotation accuracies.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals yi denotes the LLM annotation accuracies

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.723677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70bfafd6-52d9-4e8e-a797-b91e80301d73 · outbound

This paper cites Large Language Models Can Self-Improve.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Large Language Models Can Self-Improve

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.623904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ddb5ba5-2b9b-4000-8a18-fbe2b55a60cb · outbound

This paper cites MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.635830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c8b7f60-0c63-4701-888c-dcdcc7e57049 · outbound

This paper cites Efficient Intent Detection with Dual Sentence Encoders.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Efficient Intent Detection with Dual Sentence Encoders

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.601157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ace878f-ff85-441e-ae45-d2f847d49ad1 · outbound

This paper cites New Intent Discovery with Pre-training and Contrastive Learning.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals New Intent Discovery with Pre-training and Contrastive Learning

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.704280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e14911-340e-4b2c-bdec-063d2428ef9e · outbound

This paper cites TWEAC: Transformer with Extendable QA Agent Classifiers.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals TWEAC: Transformer with Extendable QA Agent Classifiers

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.612448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d39323f-e64d-429f-abf4-1048cb2d4f7d · outbound

This paper cites FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.618338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b97cea59-8b75-4c4d-b098-1dd48215103d · outbound

This paper cites Graphprompt: Unifying pre-training and downstream tasks for graph neural networks.

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals Graphprompt: Unifying pre-training and downstream tasks for graph neural networks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T20:11:41.641752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.