What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction | Paper Citation Record

Observation 59abdfec-2b79-400f-abb4-6896d381a4af · outbound

This paper cites Research Synthesis and Meta-Analysis: A Step-by-Step Approach.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Research Synthesis and Meta-Analysis: A Step-by-Step Approach

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.653529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f67cc0f-6e6e-4c9c-8dd2-dd9074bee257 · outbound

This paper cites Analysing data and undertaking meta-analyses, chapter 10, pages 241–284.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Analysing data and undertaking meta-analyses, chapter 10, pages 241–284

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.664179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0762771-aa93-47e0-aeb8-895ffc8ebf2c · outbound

This paper cites Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the prospero registry.BMJ Open, 7 (2), 2017.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the prospero registry.BMJ Open, 7 (2), 2017

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.671805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efdddffb-8142-469b-909e-5f43339c72f5 · outbound

This paper cites Higgins, James Thomas, Jacqueline Chandler, Miranda Cumpston, Tianjing Li, Matthew J.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Higgins, James Thomas, Jacqueline Chandler, Miranda Cumpston, Tianjing Li, Matthew J

Reference 4

Resolution: verified exact; doi, observed 2026-08-06T15:46:09.038582Z

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.

Observation 70ea14fd-5453-4d30-8447-05c6b28e9f97 · outbound

This paper cites Validity of data extraction in evidence synthesis practice of adverse events: repro- ducibility study.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Validity of data extraction in evidence synthesis practice of adverse events: repro- ducibility study

Reference 5

Resolution: verified exact; doi, observed 2026-08-06T15:46:09.020674Z

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.

Observation 975c4024-e2d0-4308-ada1-f84d80119446 · outbound

This paper cites Toward systematic review automation: a practical guide to using machine learning tools in research synthesis.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Toward systematic review automation: a practical guide to using machine learning tools in research synthesis

Reference 6

Resolution: malformed identifier; no resolver link, observed 2026-08-06T15:46:07.690733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0629e68-bf64-4206-99b4-91252af8cde9 · outbound

This paper cites Exact: automatic extraction of clinical trial characteristics from journal publications.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Exact: automatic extraction of clinical trial characteristics from journal publications

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.697875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd4bafa-4184-4928-a2ff-b8fe42880703 · outbound

This paper cites Summerscales, Shlomo Argamon, Shangda Bai, Jordan Hupert, and Alan Schwartz.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Summerscales, Shlomo Argamon, Shangda Bai, Jordan Hupert, and Alan Schwartz

Reference 8

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.968448Z

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.

Observation ca059850-7817-4bff-a971-e79644f87bd6 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 9

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T15:46:09.459526Z

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.

Observation 1c86dbba-aac8-4c3c-ac6b-60cf0a5c8cc7 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.784022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc08e3c2-ce9c-41ab-ae05-793e5c754ed0 · outbound

This paper cites Automating meta-analyses of randomized clinical trials: a first look.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Automating meta-analyses of randomized clinical trials: a first look

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.801622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c032b9f2-8819-4519-aed0-7709bda04041 · outbound

This paper cites Katz-Rogozhnikov, Kush R.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Katz-Rogozhnikov, Kush R

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.812345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec473968-5324-44d2-a235-b93418bdb282 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.817822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b1e172-1af5-4a79-be85-76ea657b1997 · outbound

This paper cites Data extraction methods for systematic review (semi)automation: Update of a living systematic review [version 2; peer review: 3 approved].

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Data extraction methods for systematic review (semi)automation: Update of a living systematic review [version 2; peer review: 3 approved]

Reference 14

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.928184Z

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.

Observation 094ae696-9487-4bcc-8bfd-ea6e8255c58e · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.829830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8fbea24-066b-455d-b1ca-bda23239e5b1 · outbound

This paper cites The data is in: Deciding when to automate screening in your slr, November 2023.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction The data is in: Deciding when to automate screening in your slr, November 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.834832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f63edf05-4f58-41af-89ae-082feb262b6e · outbound

This paper cites Toward automated data extraction according to tabular data structure: Cross-sectional pilot survey of the comparative clinical literature.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Toward automated data extraction according to tabular data structure: Cross-sectional pilot survey of the comparative clinical literature

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.839801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e34ed0-8485-4fcb-8124-2dad653175dd · outbound

This paper cites MetaMate: Large Language Model to the Rescue of Automated Data Extraction for Educational Systematic Reviews and Meta-analyses, 2024.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction MetaMate: Large Language Model to the Rescue of Automated Data Extraction for Educational Systematic Reviews and Meta-analyses, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.854237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c78217-16e8-4a6f-8fd3-64c498887a46 · outbound

This paper cites Chatgpt: Large language model (mar 14 version).

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Chatgpt: Large language model (mar 14 version)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.864218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac6f8e3-00ef-4460-b6f3-4ea7f1d4f000 · outbound

This paper cites Claude 2 model announcement.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Claude 2 model announcement

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.870017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 583f778e-b019-49a5-aa43-88fadb7779a7 · outbound

This paper cites Zero-shot infor- mation extraction for clinical meta-analysis using large language models.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Zero-shot infor- mation extraction for clinical meta-analysis using large language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.875116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75556778-c65e-4b3b-8f2d-8b86090c2e79 · outbound

This paper cites Performance of two large language models for data extraction in evidence synthesis.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Performance of two large language models for data extraction in evidence synthesis

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.880456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6705cf30-2390-4d27-9f7e-b02c0a6a2512 · outbound

This paper cites Automatically extracting numerical results from randomized controlled trials with large language models.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Automatically extracting numerical results from randomized controlled trials with large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.885286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe259602-0acf-4aa5-9e96-25afc38508d9 · outbound

This paper cites Exploring the use of a large language model for data extraction in systematic reviews: a rapid feasibility study.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Exploring the use of a large language model for data extraction in systematic reviews: a rapid feasibility study

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.891121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94bbea6d-b5f3-4320-89d7-15055bdf1e24 · outbound

This paper cites Lee, Shigeki Yamada, and Tomohiro Mizuno.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Lee, Shigeki Yamada, and Tomohiro Mizuno

Reference 25

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.866219Z

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.

Observation 1cfbaa80-85fd-4a5a-97d0-24a0a022a479 · outbound

This paper cites Effects of the Modified DASH Diet on Adults With Elevated Blood Pressure or Hypertension: A Systematic Review and Meta-Analysis.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Effects of the Modified DASH Diet on Adults With Elevated Blood Pressure or Hypertension: A Systematic Review and Meta-Analysis

Reference 26

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T15:46:09.370112Z

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.

Observation 96dc95e7-b78e-47d4-bdca-e36962197bcf · outbound

This paper cites Abdelrahim, Nivine Hanach, Refat AlKurd, Moien Khan, Lana Mahrous, Hadia Radwan, Farah Naja, Mohamed Madkour, Khaled Obaideen, Husam Khraiwesh, and MoezAlIslam Faris.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Abdelrahim, Nivine Hanach, Refat AlKurd, Moien Khan, Lana Mahrous, Hadia Radwan, Farah Naja, Mohamed Madkour, Khaled Obaideen, Husam Khraiwesh, and MoezAlIslam Faris

Reference 27

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.829269Z

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.

Observation 64105b66-d969-41af-a918-8da6e2c4b62b · outbound

This paper cites Effect of dietary glycemic index on insulin resistance in adults without diabetes mellitus: a systematic review and meta-analysis.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Effect of dietary glycemic index on insulin resistance in adults without diabetes mellitus: a systematic review and meta-analysis

Reference 28

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T15:46:09.285708Z

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.

Observation 8b698dba-6c1e-4100-a69b-c5908f7b0a20 · outbound

This paper cites Choi, Min-Sun Gu, Seo-Yeong Ko, Jae-Hee Kwon, Ja-Young Han, Jae Hyun Kim, and Myeong Gyu Kim.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Choi, Min-Sun Gu, Seo-Yeong Ko, Jae-Hee Kwon, Ja-Young Han, Jae Hyun Kim, and Myeong Gyu Kim

Reference 29

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.799935Z

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.

Observation 5c6db0f3-9237-4145-a5d2-9b5c829d2f1e · outbound

This paper cites V olar locking plate vs cast immobilization for distal radius fractures: a systematic review and meta- analysis.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction V olar locking plate vs cast immobilization for distal radius fractures: a systematic review and meta- analysis

Reference 30

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.774773Z

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.

Observation 34192b22-a459-443b-8287-0cf5870d8db2 · outbound

This paper cites Gpt-4o mini: Advancing cost-efficient intelligence.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Gpt-4o mini: Advancing cost-efficient intelligence

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.934074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c32e8170-e0d4-4921-9966-1a46b81557ab · outbound

This paper cites Gemini 2.0 flash.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Gemini 2.0 flash

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.939758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93682bef-d44e-4c7c-8a57-315a4becb015 · outbound

This paper cites Grok-3 language model.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Grok-3 language model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.945503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b9cbaff-4f41-4132-857c-c60de2b330d0 · outbound

This paper cites The impact of temperature on extracting information from clinical trial publications using large language models.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction The impact of temperature on extracting information from clinical trial publications using large language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.951933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bbf6358-214b-43d1-afdb-4f0aea3b2d51 · outbound

This paper cites AI-Assisted Data Extraction for Systematic Reviews in Education.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction AI-Assisted Data Extraction for Systematic Reviews in Education

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.958889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178abf96-a100-40cc-b4ea-fefa51c92b6a · outbound

This paper cites Use gemini 2.0 to speed up data processing.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Use gemini 2.0 to speed up data processing

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.965054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f654e4b5-931a-4750-a1f4-2c9e8ea67a82 · outbound

This paper cites Harnessing ai for integrative medicine: Exploring grok 3’s role in researching qigong, tai chi, yoga, and mindfulness for college students’ mental health.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Harnessing ai for integrative medicine: Exploring grok 3’s role in researching qigong, tai chi, yoga, and mindfulness for college students’ mental health

Reference 37

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.748746Z

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.

Observation 759dce94-632b-4544-a756-d882cdaf18b0 · outbound

This paper cites Microsoft adds elon musk’s grok-3 to azure, citing health- care and science use cases.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Microsoft adds elon musk’s grok-3 to azure, citing health- care and science use cases

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.347631Z

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.

Observation fc9056f3-42b0-4a30-89cd-34b59992be83 · outbound

This paper cites Reflexion: language agents with verbal reinforcement learning.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Reflexion: language agents with verbal reinforcement learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.318292Z

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.

Observation 2acec01b-d982-4110-aa42-d3a6d238ea8e · outbound

This paper cites Towards mitigating LLM halluci- nation via self reflection.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Towards mitigating LLM halluci- nation via self reflection

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:07.994474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c7a93d2-95b1-41d6-8356-4ae8b04c0c95 · outbound

This paper cites When hindsight is not 20/20: Testing limits on reflective thinking in large language models.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction When hindsight is not 20/20: Testing limits on reflective thinking in large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.295126Z

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.

Observation ccc81064-a620-4159-a80e-ba3512ca49d4 · outbound

This paper cites Dietterich.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Dietterich

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.267940Z

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.

Observation 23f4b757-ac28-47ef-8306-fc3ec919bcb0 · outbound

This paper cites A survey on ensemble learning.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction A survey on ensemble learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.018396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84df5e4-15d8-4caa-aca3-aba9d2a57a96 · outbound

This paper cites Ensemble pretrained language models to extract biomedical knowledge from litera- ture.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Ensemble pretrained language models to extract biomedical knowledge from litera- ture

Reference 44

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.645522Z

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.

Observation 8d7ef2bc-7931-463f-922d-5202489506dd · outbound

This paper cites Zhang and A.L.P.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Zhang and A.L.P

Reference 45

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.618170Z

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.

Observation 31adf290-91b9-4d02-862c-b19873f71cee · outbound

This paper cites Comprehensive testing of large language models for extraction of structured data in pathology.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Comprehensive testing of large language models for extraction of structured data in pathology

Reference 46

Resolution: malformed identifier; doi_truncated, observed 2026-08-06T15:46:08.587520Z

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.

Observation d28dc553-4477-4edf-b7d3-e393a2f59d3f · outbound

This paper cites Innocence discovery lab - harnessing large language models to surface data buried in wrongful conviction case documents.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Innocence discovery lab - harnessing large language models to surface data buried in wrongful conviction case documents

Reference 47

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.546789Z

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.

Observation 18e1f353-74a7-4807-89c8-99ee1df24e4f · outbound

This paper cites Match, compare, or select? an investigation of large language models for entity matching.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Match, compare, or select? an investigation of large language models for entity matching

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.243358Z

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.

Observation cc3c1a78-35ff-4e69-a324-9c56813ca94d · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 49

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.516502Z

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.

Observation 84af77db-91b6-4c1a-b14e-2095284f718e · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.061584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f397eca-7685-4cf9-8b04-69ba6bc821d3 · outbound

This paper cites Guyatt, Andrew D.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Guyatt, Andrew D

Reference 51

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.492238Z

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.

Observation 8614a940-0e89-4af5-add4-f99fb77eb40c · outbound

This paper cites Transforming Evidence Synthesis: A Systematic Review of the Evolution of Automated Meta-Analysis in the Age of AI.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Transforming Evidence Synthesis: A Systematic Review of the Evolution of Automated Meta-Analysis in the Age of AI

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.075310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449df189-eab1-4838-8f8f-8e5dc1abdc35 · outbound

This paper cites Agentic reasoning: Reasoning llms with tools for the deep research,.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Agentic reasoning: Reasoning llms with tools for the deep research,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.198891Z

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.

Observation 2aa669b4-d09e-46ea-aa25-0ac7f3da646a · outbound

This paper cites TART: An open-source tool- augmented framework for explainable table-based reasoning.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction TART: An open-source tool- augmented framework for explainable table-based reasoning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.171211Z

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.

Observation b81958ca-a660-4689-bb8e-db65fdbe01a3 · outbound

This paper cites Medical hallucination in foundation models and their impact on healthcare.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Medical hallucination in foundation models and their impact on healthcare

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.105709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cabcab11-7bd8-46b3-ae71-b44625490a07 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.111858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1898d8-f3f5-489c-9aee-2d67e449992e · outbound

This paper cites Potential roles of large language models in the production of systematic reviews and meta-analyses.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Potential roles of large language models in the production of systematic reviews and meta-analyses

Reference 57

Resolution: malformed identifier; no resolver link, observed 2026-08-06T15:46:08.118777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93db9ab6-c6b9-4861-98f0-f20db0315ff6 · outbound

This paper cites justification.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction justification

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.153899Z

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.

Observation e1d54069-2ad1-44a4-9a0c-74c7a7d12d35 · outbound

This paper cites other_time_points.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction other_time_points

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.136844Z

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.

Observation 69682989-e509-4562-9ede-0699148ce6d3 · outbound

This paper cites needs_transformation.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction needs_transformation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.117550Z

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.

Observation 5af7e017-6330-4c4b-9a15-b03cafc5d496 · outbound

This paper cites null"`, NOT `.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction null"`, NOT `

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.100782Z

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.

Observation 502eff7e-a05c-4706-a710-8504908387b9 · outbound

This paper cites more common in the intervention group.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction more common in the intervention group

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.078892Z

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.

Observation 03ae9405-e1de-40c5-a58f-b5f4d3b0af26 · outbound

This paper cites data_conflicts.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction data_conflicts

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.058081Z

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.

Observation cbdb9462-4a71-409a-9055-a8c6b0f3411e · outbound

This paper cites pdf_status.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction pdf_status

Reference 68

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T15:46:10.036874Z

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.

Observation be175a7f-d594-4d4a-b249-ba68e6a3e99c · outbound

This paper cites pdf_status.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction pdf_status

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.018641Z

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.

Observation b871bc30-9e35-4490-80b3-93fad8c85ad0 · outbound

This paper cites - Identify any structural inconsistencies (e.g., missing key study characteristics, incomplete sample size reporting).

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction - Identify any *structural inconsistencies* (e.g., missing key study characteristics, incomplete sample size reporting)

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:10.000536Z

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.

Observation 011d302c-57c1-4b6c-9e08-c0b603624a95 · outbound

This paper cites - Unit consistency: Verify all measurements use the correct units (e.g., blood pressure should be in mmHg).

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction - *Unit consistency*: Verify all measurements use the correct units (e.g., blood pressure should be in mmHg)

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.981621Z

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.

Observation 7e25a773-219d-4351-b77e-f33ec5ef81cf · outbound

This paper cites - Identify discrepancies and data conflicts between different sections of the paper (e.g., abstract vs.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction - Identify discrepancies and data conflicts between different sections of the paper (e.g., abstract vs

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.956642Z

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.

Observation eeed05e4-b1e0-4c03-8474-33f38239b288 · outbound

This paper cites source" the most appropriate location in the paper for this data? If not, provide a more accurate source. - Confidence Justification: Is the assigned.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction source" the most appropriate location in the paper for this data? If not, provide a more accurate source. - Confidence Justification: Is the assigned

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.929667Z

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.

Observation b82d1c6d-022f-4f65-b6be-1fa851dfde95 · outbound

This paper cites needs_transformation.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction needs_transformation

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.910425Z

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.

Observation 3c9eca83-c241-4135-8854-e64f65e33fec · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.890938Z

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.

Observation 8fdb2b6c-3a11-49f8-9877-ccc8cae1ee5a · outbound

This paper cites null"` or `.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction null"` or `

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.871709Z

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.

Observation 92559793-e3f6-4e01-bbf9-3f5fdee6ad67 · outbound

This paper cites revised_value.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction revised_value

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.855205Z

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.

Observation 9fc1478b-13be-463e-83ff-8a368299de13 · outbound

This paper cites pdf_status.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction pdf_status

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.835083Z

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.

Observation 90943ae5-6f81-415a-8a34-8356cbc00d3f · outbound

This paper cites confidence.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction confidence

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.813283Z

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.

Observation aa8d47f0-2708-41cd-a7a1-9c15b0df1e89 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.793979Z

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.

Observation d2d90d35-360b-48b9-b65e-437e63df213b · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.770068Z

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.

Observation 41fcd1e8-5048-4941-909e-7a53cd38dea4 · outbound

This paper cites Just return the final merged JSON object.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Just return the final merged JSON object

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.753155Z

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.

Observation 9385cae5-652e-45cb-8c22-60b0402bf079 · outbound

This paper cites LGL_group.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction LGL_group

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.713347Z

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.

Observation bd83a4e9-a0df-4780-ada0-9ec931fa8fcd · outbound

This paper cites Note: EXT fields may be nested.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction **Note:** EXT fields may be nested

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.694694Z

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.

Observation 6c0500bc-867b-4458-806d-71ba0e2a6d13 · outbound

This paper cites kg/m²"` and `.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction kg/m²"` and `

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.679005Z

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.

Observation 7176815e-0209-41f6-8c8e-5775018994e1 · outbound

This paper cites low glycemic load diet.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction low glycemic load diet

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.664051Z

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.

Observation 17f12667-e5e3-4b97-af9c-4857f228a268 · outbound

This paper cites null" or.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction null" or

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.649218Z

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.

Observation 1be37d85-a7de-4cf8-8428-1f2016d914b7 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.635116Z

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.

Observation 2edfcde8-35c9-4f4d-9765-3301503073e9 · outbound

This paper cites randomised controlled trial.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction randomised controlled trial

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.620028Z

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.

Observation fc808152-11b7-4421-add0-9536fa7c8b8c · outbound

This paper cites You may refer to EXT field meta-information (e.g., `source`, `notes`, `confidence`) to aid in field matching, especially when EXT uses vague or ambiguous labels.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction You may refer to EXT field meta-information (e.g., `source`, `notes`, `confidence`) to aid in field matching, especially when EXT uses vague or ambiguous labels

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.605521Z

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.

Observation cdf87145-1676-4d00-b375-3100fed7d3fa · outbound

This paper cites not reported.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction not reported

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.589766Z

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.

Observation 685b9bca-5db9-43cd-9dad-2c4663eac3aa · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.575016Z

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.

Observation 8c836ecb-5ab3-4107-a7c8-4d359f7eae8a · outbound

This paper cites null" or.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction null" or

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.558785Z

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.

Observation 606b3b47-a88b-4036-b68c-99e978ad0083 · outbound

This paper cites This is the preferred method.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction This is the preferred method

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.731507Z

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.

Observation eb4f5bfe-8964-4cb9-82f6-44340197761e · outbound

This paper cites study_characteristics.PC.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction study_characteristics.PC

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.543680Z

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.

Observation 6f81d274-411b-4662-8a29-b2a4b800eb0c · outbound

This paper cites Note: GT and EXT fields may be nested.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction **Note:** GT and EXT fields may be nested

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.528298Z

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.

Observation d9c6a707-ca25-4048-ab83-9962fac63c46 · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 98

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:46:09.513048Z

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.

Observation f85a4249-4b59-4dd7-8a96-a6d65085bd5f · outbound

This paper cites Hallucinated.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Hallucinated

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.495300Z

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.

Observation 630a5e2b-c286-48be-b87e-e5bf735924fd · outbound

This paper cites Not reported.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Not reported

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:46:09.480859Z

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.

Observation 6eb66810-3256-4c2e-ac1c-081f1c2e57ba · outbound

This paper cites an unresolved cited work.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Unresolved cited work

Reference 2010

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.993029Z

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.

Observation f2e4c449-39dc-4619-bcfe-c1fbc710d46c · outbound

This paper cites doi:10.2196/33124.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction doi:10.2196/33124

Reference 2021

Resolution: malformed identifier; doi_truncated, observed 2026-08-06T15:46:08.908021Z

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.

Observation d98a3bf5-63c6-4afe-962e-99dc9b911760 · outbound

This paper cites doi:10.18653/v1/2024.findings-naacl.237.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction doi:10.18653/v1/2024.findings-naacl.237

Reference 2024

Resolution: verified exact; doi, observed 2026-08-06T15:46:08.707784Z

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.

Observation eb66b4e2-c9ff-40f7-bcf8-a057212be15a · outbound

This paper cites Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools.

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:08.090594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers