Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification | Paper Citation Record

Observation 7b5e16ea-1c79-4375-bc14-3039da35537f · outbound

This paper cites Autores Cuellar, Jaime E.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Autores Cuellar, Jaime E

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.511560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 55865d0b-30cd-4af9-bdcf-a3c207defefa · outbound

This paper cites En este sentido, se buscó poner a prueba la capacidad del modelo para interpretar correctamente el mensaje subyacente, con formas lingüísticas desestructuradas.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification En este sentido, se buscó poner a prueba la capacidad del modelo para interpretar correctamente el mensaje subyacente, con formas lingüísticas desestructuradas

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.447960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 508962c9-bf74-46ab-aa2a-25b0471ec158 · outbound

This paper cites (2024) emplearon el análisis de sentimientos como base para desarrollar una métrica del impacto de los rumores en redes sociales en términos de daño.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification (2024) emplearon el análisis de sentimientos como base para desarrollar una métrica del impacto de los rumores en redes sociales en términos de daño

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.479660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0c50615f-6ac7-48f6-920c-d6a8527c8286 · outbound

This paper cites (País) + (nombre del Presidente) + ‘presidente’.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification (País) + (nombre del Presidente) + ‘presidente’

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.459178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation aa752d26-98c8-4ed8-9482-ff40f8dc4b28 · outbound

This paper cites El código utilizado fue construido a partir de la documentación de OpenAI para realizar análisis de sentimientos (Guzman 2024; OpenAI 2023a).

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification El código utilizado fue construido a partir de la documentación de OpenAI para realizar análisis de sentimientos (Guzman 2024; OpenAI 2023a)

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.437115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 61d55d05-85f9-4f59-a2a2-06a4e60bfaa8 · outbound

This paper cites Sin embargo, su contraposición en el grupo B, los prompts 2 y 8, que son el otro prompt de referencia y su variación modal respectivamente, no tienen tal cercanía.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Sin embargo, su contraposición en el grupo B, los prompts 2 y 8, que son el otro prompt de referencia y su variación modal respectivamente, no tienen tal cercanía

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.417120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 42bc59e5-ebe9-45c8-8ff9-683e4085db63 · outbound

This paper cites Lo anterior proporciona un marco inicial para conocer, contrastar y analizar los resultados de la prueba de Chi-cuadrado.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Lo anterior proporciona un marco inicial para conocer, contrastar y analizar los resultados de la prueba de Chi-cuadrado

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.406372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation da2b80fe-6e7b-4cdc-a261-b8e7d3dd4fc7 · outbound

This paper cites También, se observa que los prompts desestructurados, sin palabras gramaticales ni puntuación, no fueron los que mayor difirieron con el resto, como pasó en el análisis anterior.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification También, se observa que los prompts desestructurados, sin palabras gramaticales ni puntuación, no fueron los que mayor difirieron con el resto, como pasó en el análisis anterior

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.381876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c14b1c39-1784-4567-a75b-ec8407638ec4 · outbound

This paper cites Otro hallazgo está en la robustez del LLM.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Otro hallazgo está en la robustez del LLM

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.370656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 796bc8f0-d927-47c0-a08b-01c07fe27200 · outbound

This paper cites Nunca vi a el karma de actuar de manera tan instantánea.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Nunca vi a el karma de actuar de manera tan instantánea

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.426858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1ef1d238-b84d-4ad7-ae33-fd67eb351edf · outbound

This paper cites ChatGPT and the Future of Medical Writing.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification ChatGPT and the Future of Medical Writing

Reference 17

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.814350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b889a4d8-5ee4-4686-8e86-60c70c001775 · outbound

This paper cites RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.349526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5dc67c-04a6-4915-940a-b0046fea3459 · outbound

This paper cites Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.354604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 537aab2d-2f41-4273-aa5b-e70b52e00e45 · outbound

This paper cites Language models are few-shot learners.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Language models are few-shot learners

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.346417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fc1b7b00-dabf-48fd-be6e-e52ddace1c4c · outbound

This paper cites The Nexus between Information Disorder and Terrorism: A Mix of Machine Learning Approach and Content Analysis on 39 Terror Attacks.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification The Nexus between Information Disorder and Terrorism: A Mix of Machine Learning Approach and Content Analysis on 39 Terror Attacks

Reference 21

Resolution: verified exact; raw_fallback, observed 2026-08-16T12:40:04.177348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7039129b-1795-4881-83fd-9cece5205551 · outbound

This paper cites New York: Routledge.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification New York: Routledge

Reference 24

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.775924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 15451eb4-80aa-473d-ae0c-67cdfeed93dc · outbound

This paper cites Commercial Sentiment Analysis Solutions: A Comparative Study.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Commercial Sentiment Analysis Solutions: A Comparative Study

Reference 25

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.765814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e01fd8eb-fc35-4401-b056-c6791112418d · outbound

This paper cites ACOSO, SOLEDAD Y DESPRESTIGIO: Un estudio sobre las formas, las rutas de atención y el impacto de las violencias digitales contra las candidatas al Congreso colombiano en 2022.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification ACOSO, SOLEDAD Y DESPRESTIGIO: Un estudio sobre las formas, las rutas de atención y el impacto de las violencias digitales contra las candidatas al Congreso colombiano en 2022

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.334453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 675cea3e-413a-48ae-8509-d022577c9b46 · outbound

This paper cites Prompt Engineering with ChatGPT: A Guide for Academic Writers.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Prompt Engineering with ChatGPT: A Guide for Academic Writers

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.386841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f61bb027-c7a5-4749-a82f-591479507796 · outbound

This paper cites TrustLLM: Trustworthiness in Large Language Models.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification TrustLLM: Trustworthiness in Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.400497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f44bc88c-f139-4ebe-9d28-a4814a691251 · outbound

This paper cites A brief history of APIs.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification A brief history of APIs

Reference 32

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.738129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0993c987-9eda-423a-b2d7-bd585066c468 · outbound

This paper cites Analyzing European Migrant-Related Twitter Deliberations.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Analyzing European Migrant-Related Twitter Deliberations

Reference 33

Resolution: metadata mismatch; raw_fallback, observed 2026-08-16T12:40:04.113570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d2edf4de-e496-4462-8aaa-f8c48e0450d4 · outbound

This paper cites Exploring ChatGPT Capabilities and Limitations: A Survey.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Exploring ChatGPT Capabilities and Limitations: A Survey

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.410812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74151aa-05e6-47f2-aedd-934bacd0dce3 · outbound

This paper cites The language of prompting: What linguistic properties make a prompt successful?.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification The language of prompting: What linguistic properties make a prompt successful?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.417425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83bc9ee-66eb-4964-8158-6c91ad283153 · outbound

This paper cites Vasarhelyi.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Vasarhelyi

Reference 37

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.712275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f36f5871-1201-4ddb-b704-ec1c9b967799 · outbound

This paper cites Extracting financial data from unstructured sources: leveraging large language models.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Extracting financial data from unstructured sources: leveraging large language models

Reference 38

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.699837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9c1ee5f6-cde6-49c9-8d96-864e34549167 · outbound

This paper cites Generated Knowledge Prompting for Commonsense Reasoning.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Generated Knowledge Prompting for Commonsense Reasoning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.427884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcfb3d70-420f-4c40-8235-c60166c31e82 · outbound

This paper cites Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.431903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 371ef2e3-e751-4a48-917d-5fb5dd00f499 · outbound

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

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Large Language Model Guided Tree-of-Thought

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.436363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd3b46d-b972-4d3f-9621-34791dd3c25a · outbound

This paper cites Sentiment Analysis Using Dictionary-Based Lexicon Approach: Analysis on the Opinion of Indian Community for the Topic of Cryptocurrency.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Sentiment Analysis Using Dictionary-Based Lexicon Approach: Analysis on the Opinion of Indian Community for the Topic of Cryptocurrency

Reference 42

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.658884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ea17fdcb-9057-4e65-a852-a28bddf4d7d6 · outbound

This paper cites an unresolved cited work.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.414177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fb9ccc0-6939-4532-9597-8d6e6eadc045 · outbound

This paper cites Reliability Issues of LLMs: ChatGPT a Case Study.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Reliability Issues of LLMs: ChatGPT a Case Study

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.444051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 551e263f-f029-4ca5-9107-18abdafb753b · outbound

This paper cites Where Did the News Come From? Detection of News Agency Releases in Historical Newspapers.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Where Did the News Come From? Detection of News Agency Releases in Historical Newspapers

Reference 45

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.647924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 637cfd2e-c4ff-4f74-97e9-d3608e8b2d01 · outbound

This paper cites Toxic Bias: Perspective API Misreads German as More Toxic.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Toxic Bias: Perspective API Misreads German as More Toxic

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.450517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f802f80d-1291-43e1-a864-3e8aa79fc3dd · outbound

This paper cites From Twitter to Aso-Rock: A Sentiment Analysis Framework for Understanding Nigeria 2023 Presidential Election.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification From Twitter to Aso-Rock: A Sentiment Analysis Framework for Understanding Nigeria 2023 Presidential Election

Reference 47

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.626443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2ea904ec-5ea2-4bee-9cea-65b04afb1194 · outbound

This paper cites Negligent Algorithmic Discrimination.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Negligent Algorithmic Discrimination

Reference 48

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.615690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2f855b3c-dce2-4ea4-8907-eb0e49b178ca · outbound

This paper cites A Computational Look at Oral History Archives.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification A Computational Look at Oral History Archives

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.461440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d305c12b-fd07-48a0-ad3c-9d54ee79e717 · outbound

This paper cites Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.311824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 55c9bb49-0f19-4802-9d4b-814f92acc8d2 · outbound

This paper cites 33 Rolin, Kristina.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification 33 Rolin, Kristina

Reference 51

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.599259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a158a9c0-0f96-4f70-8f3e-7d05b30a7f1e · outbound

This paper cites Trust in artificial agents.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Trust in artificial agents

Reference 52

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.786427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b61fc222-60c8-45b1-8d42-ce2d57023df4 · outbound

This paper cites A perfect X-ray beam splitter and its applications to time-domain interferometry and quantum optics exploiting free-electron lasers.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification A perfect X-ray beam splitter and its applications to time-domain interferometry and quantum optics exploiting free-electron lasers

Reference 53

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T12:40:03.956618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation da77fdb3-3163-40d2-b877-cc3022ed5a86 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.485753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2efe8ba5-52f3-4674-9728-06674bc868c8 · outbound

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

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Finetuned Language Models Are Zero-Shot Learners

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.489697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf160bca-6520-485b-9df2-b11a94e4ddb1 · outbound

This paper cites Sentiment Analysis Using Deep Learning Architectures: A Review.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Sentiment Analysis Using Deep Learning Architectures: A Review

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.493713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ace041ce-ce15-4a7b-b1b6-896b665a2668 · outbound

This paper cites Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.301207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 39f5082d-9122-43b5-b40f-0571d65c8e74 · outbound

This paper cites https://doi.org/10.1145/3544548.3581388 Zanotti, Giacomo, Mattia Petrolo, Daniele Chiffi, and Viola Schiaffonati.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification https://doi.org/10.1145/3544548.3581388 Zanotti, Giacomo, Mattia Petrolo, Daniele Chiffi, and Viola Schiaffonati

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.500819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b82d6ec-ec6f-4c67-a632-0eb8bd90ed7a · outbound

This paper cites Keep Trusting! A Plea for the Notion of Trustworthy AI.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Keep Trusting! A Plea for the Notion of Trustworthy AI

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.504359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87134263-7085-427b-b371-fd48b7345a4c · outbound

This paper cites Sentiment Analysis in the Era of Large Language Models: A Reality Check.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Sentiment Analysis in the Era of Large Language Models: A Reality Check

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.507555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4f509c0-69d8-4213-8bdf-e0319299be9c · outbound

This paper cites Meta Prompting for AI Systems.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Meta Prompting for AI Systems

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.510992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50b196c0-6ff5-42c2-9ae1-f6128521b3e7 · outbound

This paper cites an unresolved cited work.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:40:04.393767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c3b9e73f-2ee4-4d4c-88d4-f4b6a5f9b97b · outbound

This paper cites Defining Trust and E-trust: From Old Theories to New Problems.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Defining Trust and E-trust: From Old Theories to New Problems

Reference 2009

Resolution: verified exact; doi, observed 2026-08-16T12:40:03.586880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 990e2a18-3511-485c-baf0-45ecacd75153 · outbound

This paper cites Toward a Model of Trust and E-trust Processes Using Object-oriented Methodologies.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Toward a Model of Trust and E-trust Processes Using Object-oriented Methodologies

Reference 2010

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.322413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2ef81270-5087-47a4-aaa7-3e72b2480f47 · outbound

This paper cites Can we trust robots?.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Can we trust robots?

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.367625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53bfe4f4-a184-4b78-92ea-f950acd2706a · outbound

This paper cites Prediction of Sentiment Analysis on Educational Data Based on Deep Learning Approach.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Prediction of Sentiment Analysis on Educational Data Based on Deep Learning Approach

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.477550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63f3ea1e-54d0-4420-b7a9-c350c2920a6f · outbound

This paper cites Su impacto en diferentes áreas del conocimiento ha sido inmediato.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Su impacto en diferentes áreas del conocimiento ha sido inmediato

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.501476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 65074678-6b14-462f-9f05-3017af97e37f · outbound

This paper cites Biden vs Trump: Modelling US General Elections Using BERT Language Model.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Biden vs Trump: Modelling US General Elections Using BERT Language Model

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T12:40:03.360503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 794c5862-b3a0-446e-8039-aa32a9b16527 · outbound

This paper cites A pesar del reciente auge de los LLM como ChatGPT, ya se han documentado varias limitaciones del modelo.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification A pesar del reciente auge de los LLM como ChatGPT, ya se han documentado varias limitaciones del modelo

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.490514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f3a8b2a0-df2e-44e3-ac30-84908eb3698b · outbound

This paper cites verdad científica.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification verdad científica

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.469906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 69514ae1-9e7b-4e62-829b-914c5e817ac2 · outbound

This paper cites Trust as reliance in computer artifacts means that we expect an object to do something to help us attain our goals.

Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification Trust as reliance in computer artifacts means that we expect an object to do something to help us attain our goals

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:40:04.359625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers