Pith. sign in

Paper Citation Record · LEDGER

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data

As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2606.07537.

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

pith.paper-citation-record.v1
2606.07537 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T08:48:53.634257Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

15 of 15 outbound references displayed

  • verified exact3
  • verified fuzzy12
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2c161d4a-e585-4155-b05f-35402052c2ef · outbound

This paper cites Large language models hallucination: A comprehen- sive survey.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Large language models hallucination: A comprehen- sive survey

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-07-01T08:55:34.956962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:75e92441bc16bfa76ff9c51e7799344c9a22b0ae50b3f5859145c7cb65a72369

Observation 9e5be92c-8caf-40ab-a21b-5a980970022c · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-07-01T08:55:34.954045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:1ddcd0e96e46bb116eae1e43479b304d7cee2fb98583e5f47b1eb11984a1fe14

Observation 5b37bbcd-d95a-4fd8-83c9-3b1e56afa987 · outbound

This paper cites Attention is all you need.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Attention is all you need

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.142079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:3bcd173a75300aae14374ec068ae670b71a03fb69e94791cf5aa2e3ef3ab91cf

Observation 34184b61-addd-4ce5-a680-fb0ca41f279c · outbound

This paper cites Language models are few-shot learners,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Language models are few-shot learners,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.138033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:47110f4c46813d8165acfa4c056ff97b904bbd4b5e6e4c2a3eb8e3758c23f534

Observation 21855cf4-f60e-43f8-9a1f-b55ce33eea99 · outbound

This paper cites Sequence level train- ing with recurrent neural networks,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Sequence level train- ing with recurrent neural networks,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.141895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:8a76b29284aa6fda55ccff5489dfdbf9cec47a5cc9c288df541c46f981937039

Observation 5e83d4d7-29cf-43d9-ba01-6e17f323ed71 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Self-refine: Iterative refinement with self-feedback,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.146019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:04ae7b64289731260215321d3d6b226a7f2d83cdc651aeb8de69a7a83a7708d0

Observation d5926ff0-fe70-43c2-bee2-1b4455909870 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Chain-of-thought prompting elicits reasoning in large language models

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.129916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:b84844528cb53f59c66b73043cc673c0dc4c8ffea67c36fbe4a944aa974b2189

Observation 5d688055-f066-45e4-b434-da4f8606a12f · outbound

This paper cites Lost in the middle: How language models use long contexts.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Lost in the middle: How language models use long contexts

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.148963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:1aef3eb97d343559816153800940f5e3ce349b185ecac7298f06700ec2db4502

Observation 451e114d-4183-4533-92c0-77bcb336ddc7 · outbound

This paper cites TruthfulQA: Measuring how models mimic human falsehoods,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data TruthfulQA: Measuring how models mimic human falsehoods,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.143976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:0ab5961a75277c912d1c7ceebdd2fdeb89ab4bf741e8f1c643cd973bf232ac1b

Observation 94489556-b7b0-4148-9394-855477aab918 · outbound

This paper cites A mathematical framework for transformer circuits,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data A mathematical framework for transformer circuits,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.126837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:94513f65f2f6d08ebea198d78bf7c31f6961072c5b1e25ccba3d2afe58d30e13

Observation cf7ae9cd-4c46-4934-b918-01380bea4e9b · outbound

This paper cites The curious case of neural text degeneration,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data The curious case of neural text degeneration,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.133974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:d6bf637ebe40044eee715545b6ca3caa2b3f0ceb119a0a1496007c2ed98802a6

Observation 7dcba9bc-4029-4dab-89ca-ea8ae83b734d · outbound

This paper cites AI models collapse when trained on recursively generated data,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data AI models collapse when trained on recursively generated data,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.148180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:7a5e2e56a3fbadea045255ff3eb2aaf8ef8643f79279c423b456809cc9ac41a0

Observation f27db743-f5f6-43e7-9171-e2525e83bdbb · outbound

This paper cites On the dangers of stochastic parrots: Can language models be too big?.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data On the dangers of stochastic parrots: Can language models be too big?

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.139883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:c84ec6f5081ecd92c0dd262ce8358a061f390b12460f85c51d6cb7c3608b0c6c

Observation e7306be7-a617-4736-b314-290d85894f1e · outbound

This paper cites Language models are unsupervised multitask learners,.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Language models are unsupervised multitask learners,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T12:42:26.133736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:177d82e3c8fc4795e06fdecf318114c5d4e0f148650fe5a4185ec6f7c2a1f0f6

Observation 26ba6dd8-7e24-4beb-bd73-e1185dc13510 · outbound

This paper cites Scaling Laws for Neural Language Models.

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Scaling Laws for Neural Language Models

Reference 15

Resolution
verified exact
local_arxiv, observed 2026-07-01T08:55:34.951497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-07-01T08:48:53.634257Z digest=sha256:0ce0028f179d65b39e8ca19250f0fb865d6115d1700866be7eadc4c8080ce271

Pith citing papers

No inbound Pith citation observations are available.