Files
imbad0202__academic-researc…/plugin-evals-citation-check/02-apa-zh-mixed-overclaim/prompt.md
T
Edward Cheng-I Wu 90f2176cd5 evals: add claude plugin eval suite for the academic-paper citation-check flow (#859)
* evals: add `claude plugin eval` suite for the academic-paper citation-check flow

Eight cases (six fire, two negative) under plugin-evals-citation-check/,
graded as a with/without-plugin ablation. Fire cases carry a synthetic
source pack so the four author-defined citation failures (no source on
file, wrong authors, hedged finding cited as established, retracted or
concern-flagged paper cited as live) are detectable offline. Styles: APA 7
(en / zh-TW mixed / es), IEEE, Vancouver (style unnamed), Chicago NB.
Cases pin model: sonnet; run with --judge-model opus.

Calibration (two pilots, 2026-09-13) and caveats are in the suite README.
The with-plugin arm cannot load the mode prompt in the eval sandbox
because the command stub references plugin files by relative path
(#857), and plain-language prompts fired the skill in 3 of 6 cases (#858;
the Spanish case is one data point for #850). No uplift figure is claimed.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EEbmXsHyQ3dzYoep74zSmH

* evals(citation-check): apply cross-model review findings and re-calibrate

Twelve of thirteen review findings applied: replace the disputable
four-author "et al." planting in 04 with a year mismatch; make the clean
citations in 02 and 06 supported by their abstracts; replace real Taiwan
journal names in 02 with fictional ones; tie the 08 presence regexes to an
"unused" statement; require metadata preservation and reject audit content
on the 07 conversion negative; add no-overreach to 05; turn the 02 language
check into an llm grader; exempt unchanged entries in a complete corrected
list from no-false-positive and drop its DOI claim; drop the 04
style-name regex (both arms fixed the year without naming the style).
The one rejected finding (08 skill check "display-only") was wrong: it
carries arm: both and is scored; README says so.

Pilot 3 on the revised suite: $4.65, max 142 s / 7 turns / $0.45 per run;
04 and 08 re-run clean after the last two grader fixes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EEbmXsHyQ3dzYoep74zSmH

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-13 10:01:19 +08:00

4.5 KiB
Raw Blame History

max_turns, timeout_seconds, allowed_tools, model, runs
max_turns timeout_seconds allowed_tools model runs
20 600
Read
Glob
Grep
Skill
sonnet 3

請幫我檢查這篇稿子的引用。格式是 APA 7 中文版,照台灣的慣例。附上(一)稿子節錄、(二)參考文獻、(三)來源包:我手上真的有的每一篇文獻,照刊出版本抄的題名、作者、年份、出處、摘要。來源包是完整的,不在裡面的就是我沒有那篇。

(一)稿子節錄

自主學習策略與線上課程完成率呈正相關王大明、李小華2022且不同自主學習剖面的學生在課程完成率上差異明顯Okafor, 2020。陳志明、林美玲、張建國2020以 1,200 名大學生為樣本發現時間管理策略與課程完成率呈中度正相關。林美玲2021進一步證實自主學習動機能顯著提升線上學習成效且效果量達中等以上。跨國比較方面Kim 與 Park2021在韓國與美國兩地的研究顯示同步互動頻率是線上課程滿意度的最強預測因子本研究的假設一即以此為基礎。黃世杰2019的質性研究則指出學生對平台介面的熟悉度會影響其自我監控行為。

(二)參考文獻

Kim, S., & Park, J. (2021). Synchronous interaction and satisfaction in online courses: A two-country comparison. Journal of Digital Pedagogy, 17(2), 133152. https://doi.org/10.5555/jdp.2021.1702

Okafor, C. (2020). Self-regulation profiles of first-year online learners. Distance Learning Quarterly, 33(4), 401419. https://doi.org/10.5555/dlq.2020.3304

王大明、李小華2022。自主學習策略與線上課程完成率之關聯。自主學習研究學刊25(1)128。https://doi.org/10.5555/etr.2022.2501

林美玲2021。自主學習動機、學習投入與線上學習成效以北部某大學為例。北區高教探究14(3)5582。https://doi.org/10.5555/jhe.2021.1403

陳志明、林美玲、張建國2020。大學生時間管理策略與線上課程完成率。時間管理與學習研究23(2)77104。https://doi.org/10.5555/cij.2020.2302

黃世杰2019。平台熟悉度與自我監控線上學習者的質性探究。線上學習實務評論11(4)2346。https://doi.org/10.5555/jelt.2019.1104

(三)來源包

  1. Synchronous interaction and satisfaction in online courses: A two-country comparison — Kim, S., & Park, J. (2021). Journal of Digital Pedagogy, 17(2), 133152. 摘要Across 1,860 students in Korea and the United States, synchronous interaction frequency was the strongest predictor of course satisfaction in both samples (Study 1 survey; Study 2 platform log data). 備註:期刊於 2023 年對本文發布 Expression of Concern指出 Study 2 的平台日誌資料取得程序有疑慮,調查進行中。

  2. Self-regulation profiles of first-year online learners — Okafor, C. (2020). Distance Learning Quarterly, 33(4), 401419. 摘要Latent profile analysis of 712 first-year online learners yields three self-regulation profiles; the "planful" profile completes courses at nearly twice the rate of the "reactive" profile.

  3. 自主學習策略與線上課程完成率之關聯 — 王大明、李小華2022。自主學習研究學刊25(1)128。摘要以 948 名大學生為樣本自主學習策略量表總分與線上課程完成率呈中度正相關r = .41),其中目標設定分量表的預測力最高。

  4. 自主學習動機、學習投入與線上學習成效:以北部某大學為例 — 林美玲2021。北區高教探究14(3)5582。摘要以北部某大學 326 名學生為樣本,學習投入對線上學習成效有顯著正向影響(β = .38)。自主學習動機對學習成效的直接效果未達顯著(β = .07p = .21),僅呈微弱正向趨勢;動機透過學習投入的間接效果達顯著。研究限制一節指出,單一學校樣本限制了推論範圍。

  5. 大學生時間管理策略與線上課程完成率 — 陳志明、林美玲、張建國2020。時間管理與學習研究23(2)77104。摘要以 1,200 名大學生為樣本時間管理策略與課程完成率呈中度正相關r = .36)。

  6. 平台熟悉度與自我監控:線上學習者的質性探究 — 黃世杰2019。線上學習實務評論11(4)2346。摘要訪談 28 名線上學習者,發現平台介面熟悉度影響學生的自我監控行為與求助時機。