Pith. sign in

Paper Citation Record · LEDGER

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models

As of 15 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 3 inbound Pith citation observations for arXiv:2412.11385.

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

pith.paper-citation-record.v1
2412.11385 v1

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:02:39.725628Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:12:21.995870Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T05:30:23.456663Z

Reference resolution

57 of 57 outbound references displayed

  • verified exact1
  • verified fuzzy1
  • unresolved55
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

3
pith, observed 2026-08-10T05:30:23.456663Z

Outbound references

Observation 098505f0-9da2-48ad-a95a-d3f91c452ee8 · outbound

This paper cites Self-Consuming Generative Models Go MAD.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Self-Consuming Generative Models Go MAD

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.464596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.464596Z digest=sha256:e01df00170f36e0ba57ec50b6db7c8a29318a5584d68cf95dbc7754ed536bce8

Observation bbed51b7-49c8-41a7-b3c8-edb19911ef9f · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.642934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.469441Z digest=sha256:6babb2a273bee52f83dcbfb229bd33493dd9e1776b108277c16df4b12159d90d

Observation 699f9400-7932-4715-81ea-dc853c6d7a66 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.629102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.473619Z digest=sha256:d36a8048d2079d11dd17845eec7368668fb2d3721ecb14f0410f09096dc59ff4

Observation 37597351-7ede-412e-bcf7-547cb9633a1c · outbound

This paper cites Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.477913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.477913Z digest=sha256:2a8ad05493f6f52a558ebb1a239bd9a861c36feb81aa10d5ffed4a3f87b1dea0

Observation 4c2a4e93-b684-4864-a43c-a5b44b5a76f4 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.616267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.481510Z digest=sha256:8e6fa6bdc801d8e2d1c55524a6b1dfd24faff963053a794a45269bd27874cad2

Observation eb7c16a7-f561-49fb-8b37-e4bb51413b9e · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.485232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.485232Z digest=sha256:019334feba2aae4e8d29c41a9a0893f63082c3cb13b66aa9979d41676d063b45

Observation 718a6a70-bbeb-44ad-a0d9-864506ee3933 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.492120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.492120Z digest=sha256:5257add41a805f09b6e126e0bec104f5c782ac470f36686fb128504072349692

Observation e86f24b1-d0c6-4710-8b9b-5fe0f120c243 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.588675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.496407Z digest=sha256:b9d48eee630aa61e4a01dc84911055d66fecdad540e115d88e20532008f2d5fc

Observation 19d4b425-cda5-4544-8c31-77d3b360663d · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.574311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.501077Z digest=sha256:a5c2538d98952ba8103e98c4bde6fbed4a89c6b29eb8111562680b741c004f4c

Observation 819bd7ac-16f8-4675-a46f-c4fef14e79fb · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.561266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.505015Z digest=sha256:a01deb8a35a4486186df858490f074e9bb81dc194d0051c96e2994782b490bfb

Observation cce9f4b1-d42b-44c2-802b-16ae67df9e5d · outbound

This paper cites The Impact of Large Language Models in Academia: from Writing to Speaking.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models The Impact of Large Language Models in Academia: from Writing to Speaking

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.509806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.509806Z digest=sha256:b5c4f1d73528ca03a45773a7bb8e478e1249b4e660318c14d903656904648e4c

Observation e26725d2-ef44-4008-ba2f-2932c8ddf88b · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.514227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.514227Z digest=sha256:a2600ec8f83decbc235c420e714eac446bcb51b1134a9179e56eed9ec42a9545

Observation 41dce68e-add3-4b04-9581-2ef7c7ba5725 · outbound

This paper cites ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literature.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literature

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.519108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.519108Z digest=sha256:6a99d02d9471a7520702cf5a35fc7e9eea0d7ae44aedf9727a84b1427da9fef4

Observation 407b8f85-323c-47db-8170-d31a7a0c6823 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.540219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.524454Z digest=sha256:00715b5a523d32885ace45aad10f6ac0f5b48498da3efa4bbfaf20bc881862cf

Observation 7b5958dd-118f-4318-936a-bea31c1540dd · outbound

This paper cites a ussler and Tom Juzek. 2017. https://publikationen.uni-tuebingen.de/xmlui/handle/10900/77066 Hot topics surrounding acceptability judgement tasks . In S. Featherston, R. H \.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models a ussler and Tom Juzek. 2017. https://publikationen.uni-tuebingen.de/xmlui/handle/10900/77066 Hot topics surrounding acceptability judgement tasks . In S. Featherston, R. H \

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:02:40.527759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.530493Z digest=sha256:ab5fcde6f23dbcefc12a335e0c7792857d961f5427ff8bf1b55d46a859ffdeb9

Observation 140932fe-be73-42a6-a981-16493ebebfff · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.513510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.534596Z digest=sha256:fc6d00b27f55ebece1379b133be63deda84085c0bfcd063e8a137914beda5889

Observation c09e8fc1-c15d-425e-99f5-5d5b85fe5339 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.500608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.539176Z digest=sha256:47352b5f6dd96d21d265f0932d972006327d073440be3f7dc03352cc6c8da4aa

Observation 51c3c825-eb20-44ea-8302-34cbd812e104 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.488320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.543444Z digest=sha256:322fc60c7cd2312f3fe6c58ae38c2a173c9809d10cd812f9b4027941cef4ffff

Observation 328bb491-0f87-4185-8010-8de6f65f11a5 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.475316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.547691Z digest=sha256:edc4619a3802963692dbc8d4ff49f03fb4e052074f59e8a4dd978ba5956eea59

Observation 6ae2ce1a-2120-4d09-92e9-5752afa75ef9 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.463680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.553886Z digest=sha256:63ba93f30cc38cab88dabee3aa015d5314ef929ca59b858199557ac61b912666

Observation d1f0a5ec-7847-4ee0-8c7c-f3bb297adf53 · outbound

This paper cites Delving into LLM-assisted writing in biomedical publications through excess vocabulary.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Delving into LLM-assisted writing in biomedical publications through excess vocabulary

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.558999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.558999Z digest=sha256:9c304963c976cc6f42ad2b5e0531e4ac7d4ed03c033039d5c34a5d38aa12c046

Observation 90be9cd0-68a7-47a3-8255-77b5fd60f01b · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.564857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.564857Z digest=sha256:318703b1abbabf45037387e964a2b4d996a5ae980529e03ce7f2088ed649e736

Observation 7801e88f-2f16-42ea-aec3-f4ed3021c75e · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.569635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.569635Z digest=sha256:2dc2e88a67c45819088a936b668207e7c5c4174aea80554618a5b1f95207c615

Observation cf120133-c47d-4d72-85d7-bd34f9d08b01 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.445051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.573699Z digest=sha256:bae197d8605d1bc83858186685cd9c415cb0338efe109c588dd658e03433d2a8

Observation bab2c979-b0f1-4205-83b2-7f9f8921201b · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.434022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.577584Z digest=sha256:95edea89e3da7705a6c14d5bc0cc0c9f3f36e1980a8029d09357095892599e81

Observation 9df96415-65b6-43cb-a3c2-799ddc3279a0 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.421590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.583166Z digest=sha256:e7abbd585c2c8c559238d2e53a59813262b366b67adcfd2728d3fa752c63ef5e

Observation 4da2632e-b2a7-42f7-bdb0-97644cc1ae9d · outbound

This paper cites Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.587144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.587144Z digest=sha256:e6fa75bbe4f31525de68fb0faffed615f608858ae6f0c89384bece9d5dfc0a40

Observation 5e7691b5-e2d1-446a-aa66-776edef4220d · outbound

This paper cites Mapping the Increasing Use of LLMs in Scientific Papers.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Mapping the Increasing Use of LLMs in Scientific Papers

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.592222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.592222Z digest=sha256:4d1c335108e64bd5687d7b0b36e95479f86800daa58b6e2614568adbf55654b3

Observation 6ebb589c-9c82-4868-b764-4d579785989b · outbound

This paper cites Towards the relationship between AIGC in manuscript writing and author profiles: evidence from preprints in LLMs.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Towards the relationship between AIGC in manuscript writing and author profiles: evidence from preprints in LLMs

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.597020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.597020Z digest=sha256:c6042ad16f7b7c70bf1e8e8869eb1cc29edca21e1015294c626a965a08d95e20

Observation f8b5835f-e729-45c6-a945-b4aa02052cba · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.409844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.604950Z digest=sha256:b42059780cfc03af980952358364f65362df43f7f583dcc67ee61315097669a1

Observation 9dfcd2c4-ee91-4bd0-a72b-ac3ec5bc4c95 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 31

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.397128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.613373Z digest=sha256:43af64f09c3fa1ba45cfdfe58cae93125dc51a7bbea2dc734f9fe79646c908c4

Observation b8325231-224b-4ef2-99ab-7c50909a9d1c · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 32

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.383954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.617280Z digest=sha256:cda76f527505615eba0a8f2511aae81070f1400967a985b8687f6dfcb75c061e

Observation 89ddd9d1-7a6d-4fc4-9a2d-c618012471e3 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.371845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.620846Z digest=sha256:d067bc711424391984328ee38a0fa2136184e89ff2c441fc1298cac9a4c33842

Observation 21f92e3f-f670-44a0-ab04-8d2242cc253d · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.360716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.624629Z digest=sha256:8317f2f69a2385dbae352496f25bfccd1dea679c3489a5c05f0b70e6a2bce10b

Observation 48035704-52e0-4e1d-804f-bb7488ad8761 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 35

Resolution
verified exact
raw_fallback, observed 2026-08-11T15:02:39.988572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.628054Z digest=sha256:f2111441702b82fa072d5063e9f1384a38c43042629a1573248929122a7177b1

Observation dfcbd27a-c3e9-4e7f-9a88-ee26bbc58ccb · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.348536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.632075Z digest=sha256:ccd69e4b2ffcb363c2f1856fb5ac1f75139e2cd339dbfcb3edd3ba6fa1e86eae

Observation 97841b47-d2a8-4b78-9a80-61ec6b8b4247 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.635166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.635166Z digest=sha256:f0ffd7bb688b971ff08beb07d05e96720d742f93288331055d12415bea8a3bd7

Observation 3a88b4be-0a91-45e4-8b53-560f9dc9ec96 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.336312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.639723Z digest=sha256:b41d57abf01dea6d6be9410aa9f985e17354d13bbec9ea2eced7759de1ea697b

Observation f2a85eaf-7c8e-47c4-8fdd-7db308f93dff · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.643998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.643998Z digest=sha256:70fbc2b7dace4d0117ac67f072ab73ecf7ab9158f05f3a9d25293eff5eb0cc51

Observation b8977726-f7c7-4434-993f-9c9eb30031c4 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.316869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.648252Z digest=sha256:bebe255893d1520cda885b79955a523e0fc50835783870c8dfa43976b7f2b080

Observation 2c36d081-b44c-41bd-bf12-ea4597ab7ccb · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.304082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.651932Z digest=sha256:6c3786db4c71b2e9a049054eb7aaea72e20a04f842b72b2fd5820e7d926281c1

Observation aa054e70-4ed7-4dba-8bfa-484f2c34ef80 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.292416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.655897Z digest=sha256:b8110287fe07e86843743dd7740ae2fc8f3111f5f2b33abfca80a11772c28ae8

Observation 64748305-ae4c-4c01-9f23-fe5fff6febdb · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.280163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.659794Z digest=sha256:ecd3b9c0ab2e30b450356908363544fb90a2db2c8ef5de322a50f485186e186d

Observation 33ca5707-aeb0-4576-af7c-2f1f19b4a31a · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 44

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.267569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.665217Z digest=sha256:c7f89948d93d2acaeff53c8543a1478ff976c45f097acf17cc1368b807f61a9a

Observation d74afef0-34e8-456d-891a-93e827ff4e61 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.255835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.669138Z digest=sha256:aeb8a4b19031e56a0434a82cf69a7384db249ba4911135a4a1804a6a58feb212

Observation 40ee536c-30d1-4597-9821-804a0306f2fd · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.673335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.673335Z digest=sha256:863015aadf78001bd66b4f65f68ea75cdae59431a048f9141a995fca3cf228d1

Observation 8e420eba-c6f8-404a-836e-7f2472383adb · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 47

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.238179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.677415Z digest=sha256:5ca51bfc1e7c77cb6002caf8aefcee8c260e61dc4548188f96dc4a935d61149c

Observation 1dd8f647-4ae9-4f70-a210-cfa6278356a3 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.681519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.681519Z digest=sha256:df0711d9bf5b37e6885fe7059cb413462752a75b5d06f11711f32724c0d81603

Observation b7823f30-20c7-4932-a6fc-9acfbdbf0b5f · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.685717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.685717Z digest=sha256:a63f3c7ea5169b59b131307ed5f433e3caa532e557f6fbf0fed65954a8f8658d

Observation ea9884f2-6958-4bdb-937e-8cbcfc536b8d · outbound

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

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.690656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.690656Z digest=sha256:c2f2ae045d98e2951c25838120d40785fc6af034b4124f061fd48dca10a5672b

Observation d1f084ce-fe8a-44c5-b087-01e14354c6a1 · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-11T15:02:40.220594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-11T15:02:39.695571Z digest=sha256:c85e406796465325be23a810e5d4aaae7b81d16b748f0eaf80570af2263b495b

Observation 479e8048-d0d5-43c3-9a0d-ca05c93d2d0a · outbound

This paper cites an unresolved cited work.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Unresolved cited work

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.700944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.700944Z digest=sha256:2e5f136c6135ca535e1311c20cf92855eb5a97261a31e5b6bf83141dc8698515

Observation 24228682-6ed1-4983-b481-4a139ac5ef26 · outbound

This paper cites Empirical evidence of Large Language Model's influence on human spoken communication.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Empirical evidence of Large Language Model's influence on human spoken communication

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.705996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.705996Z digest=sha256:aa3ad242babe58a0c3fa503b1d1c824e11884ffd5241d040528bb97f540f23f6

Observation 60bb11a3-0ad5-42a5-bdf5-a758294ed8aa · outbound

This paper cites Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.712292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.712292Z digest=sha256:4ec42d93143916a5cce36e6520002e1aafd8659b1de5086d935ef8f2818ae522

Observation 56daf52d-f173-454a-96d1-74895e2c27ac · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Fine-Tuning Language Models from Human Preferences

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.716831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.716831Z digest=sha256:984f48cb8800f1d39937a2de145b23600e01ad8f60a9aee3dca0c20f2c3d4e01

Observation c4e2b19b-b8b4-4b08-b1ba-06acb199cf84 · outbound

This paper cites online" 'onlinestring :=.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models online" 'onlinestring :=

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.721028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.721028Z digest=sha256:fad4ea3512bc68994935bb65021b399b94e1d3c5316a030939bf3a6c30668efa

Observation 02bd1ccc-3fce-46c6-9c71-ecde52744c36 · outbound

This paper cites write newline.

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models write newline

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-11T15:02:39.725628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:02:39.725628Z digest=sha256:4b0ffc4c22636251de0a7546f36a4c485c310cbc6de15d7e966ec56aadde3a23

Pith citing papers

Observation e6968cc5-ea60-4bff-ab94-c37b77981e78 · inbound

Domain Regeneration: How well do LLMs match syntactic properties of text domains? cites this paper.

Domain Regeneration: How well do LLMs match syntactic properties of text domains? Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-15T22:12:21.995870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T22:12:21.995870Z digest=sha256:284707fa3cb40b791b72b87d4005d8e02951dd38c778e064ea1bbb659dcf7c4c

Observation c2c65234-96f7-46f1-b363-99954cfc9434 · inbound

Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback cites this paper.

Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-08-06T05:23:13.710345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-06T05:23:13.271917Z digest=sha256:8017c542763b1d2048a4759b5cb84a84180850748f6e88797d299e61c4376aa2

Observation 19fd96cc-7a26-4dfb-92b5-49e260a5df90 · inbound

Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it cites this paper.

Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T07:19:19.125548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T07:19:19.125548Z digest=sha256:22742fd4907985c8a8a06b502c1a5ad410e7be3f4b43bdddedde3a4ef9303992