diff --git a/quarto/contents/core/frontiers/frontiers.bib b/quarto/contents/core/frontiers/frontiers.bib index 52542d2496..a50d14715a 100644 --- a/quarto/contents/core/frontiers/frontiers.bib +++ b/quarto/contents/core/frontiers/frontiers.bib @@ -373,6 +373,22 @@ source = {Crossref}, } +@article{koomey2011web, + title = {Implications of Historical Trends in the Electrical Efficiency of Computing}, + author = {Koomey, Jonathan and Berard, Stephen and Sanchez, Marla and Wong, Henry}, + journal = {IEEE Annals of the History of Computing}, + booktitle = {IEEE Annals of the History of Computing}, + publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, + volume = {33}, + number = {3}, + pages = {46--54}, + doi = {10.1109/mahc.2010.28}, + issn = {1058-6180,1934-1547}, + url = {https://doi.org/10.1109/mahc.2010.28}, + source = {Crossref}, + date = {2011-03}, +} + @article{landauer1986much, title = { How much Do People Remember? Some Estimates of the Quantity of Learned Information in Long-term diff --git a/quarto/contents/core/privacy_security/privacy_security.bib b/quarto/contents/core/privacy_security/privacy_security.bib index 8c83725601..20db902767 100644 --- a/quarto/contents/core/privacy_security/privacy_security.bib +++ b/quarto/contents/core/privacy_security/privacy_security.bib @@ -249,6 +249,20 @@ editor = {DEF CON}, } +@inproceedings{carlini2021extracting, + title = {Extracting Training Data from Large Language Models}, + author = { + Carlini, Nicholas and Tramer, Florian and Wallace, Eric and Jagielski, Matthew and + Herbert-Voss, Ariel and Lee, Katherine and Roberts, Adam and Brown, Tom and Song, Dawn and + Erlingsson, Ulfar and Oprea, Alina and Raffel, Colin + }, + year = {2021}, + booktitle = {30th USENIX Security Symposium (USENIX Security 21)}, + publisher = {USENIX Association}, + pages = {2633--2650}, + url = {https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting}, +} + @article{carlini2024stealing, title = {Stealing Part of a Production Language Model}, author = { diff --git a/quarto/contents/core/robust_ai/robust_ai.bib b/quarto/contents/core/robust_ai/robust_ai.bib index c31decf869..1ea729aa8b 100644 --- a/quarto/contents/core/robust_ai/robust_ai.bib +++ b/quarto/contents/core/robust_ai/robust_ai.bib @@ -1080,6 +1080,22 @@ organization = {Citeseer}, } +@misc{quinonero2009dataset, + title = {Dataset Shift in Machine Learning}, + author = { + Qui\~{n}onero-Candela, Joaquin and Sugiyama, Masashi and Schwaighofer, Anton and Lawrence, Neil + D. + }, + journal = {The MIT Press}, + publisher = {The MIT Press}, + pages = {xi-xvi}, + doi = {10.7551/mitpress/7921.003.0002}, + isbn = {9780262255103}, + url = {https://doi.org/10.7551/mitpress/7921.003.0002}, + source = {Crossref}, + date = {2008-12-12}, +} + @inproceedings{rashid2012intermittent, title = {Intermittent Hardware Errors Recovery: Modeling and Evaluation}, author = {Rashid, Layali and Pattabiraman, Karthik and Gopalakrishnan, Sathish}, diff --git a/tools/scripts/content/validate_citations.py b/tools/scripts/content/validate_citations.py index 7fb8393c69..f43d41d8a6 100755 --- a/tools/scripts/content/validate_citations.py +++ b/tools/scripts/content/validate_citations.py @@ -60,6 +60,12 @@ def extract_citation_keys(qmd_file: Path) -> Set[str]: # Pattern matches @word with letters, numbers, hyphens, underscores, colons, dots citation_keys = set(re.findall(r'@([\w\-_:.]+)', content)) + # Strip trailing punctuation (periods, commas) that might be captured + citation_keys = {key.rstrip('.,;:') for key in citation_keys} + + # Filter out DOI-style citations (start with numbers like 10.1109) + citation_keys = {key for key in citation_keys if not re.match(r'^\d+\.\d+', key)} + # Filter out common false positives that aren't citations filtered_keys = { key for key in citation_keys