From fffb6c9969ad2b99db57b805be4192040250637e Mon Sep 17 00:00:00 2001 From: Martin Czygan Date: Fri, 8 Oct 2021 22:18:04 +0200 Subject: docs: report tweaks --- docs/TR-20210808100000-IA-WDS-REFCAT/main.pdf | Bin 128892 -> 130701 bytes docs/TR-20210808100000-IA-WDS-REFCAT/main.tex | 30 +++++++++++++++----------- 2 files changed, 17 insertions(+), 13 deletions(-) (limited to 'docs') diff --git a/docs/TR-20210808100000-IA-WDS-REFCAT/main.pdf b/docs/TR-20210808100000-IA-WDS-REFCAT/main.pdf index 1fb8f0c..4d34e91 100644 Binary files a/docs/TR-20210808100000-IA-WDS-REFCAT/main.pdf and b/docs/TR-20210808100000-IA-WDS-REFCAT/main.pdf differ diff --git a/docs/TR-20210808100000-IA-WDS-REFCAT/main.tex b/docs/TR-20210808100000-IA-WDS-REFCAT/main.tex index 8651031..11ea1fa 100644 --- a/docs/TR-20210808100000-IA-WDS-REFCAT/main.tex +++ b/docs/TR-20210808100000-IA-WDS-REFCAT/main.tex @@ -12,6 +12,7 @@ \usepackage{nicefrac} % compact symbols for 1/2, etc. \usepackage{caption} \usepackage{datetime} +\usepackage{float} \providecommand{\keywords}[1]{\textbf{\textit{Index terms---}} #1} \setlength{\parindent}{0pt} @@ -203,14 +204,14 @@ and \emph{refcat} overlap to the most part, as can be seen in~Table~\ref{table:c \begin{center} \begin{tabular}{lll} \toprule - \bf{Set} & & \bf{Count} \\ + \bf{Set} & & \bf{Count} \\ \midrule - COCIv11 (C) & & 1,186,958,897 \\ % zstdcat -T0 6741422v11.csv.zst | pv -l | wc -l - \emph{refcat-doi} (R) & & 1,303,424,212 \\ % zstdcat -T0 /magna/refcat/2021-07-28/BrefDOITable/date-2021-07-28.tsv.zst | pv -l | LC_ALL=C sort -T /sandcrawler-db/tmp-refcat/ -S70% -k3,4 -u | zstd -c -T0 > uniq_34.tsv.zst # LC_ALL=C wc -l uniq_34_doi_lower_sorted.csv - C $\cap$ R & overlap & 1,046,438,515 \\ - C $\setminus$ R & COCIv11 only & 140,520,382 \\ % 86,854,309 \\ - R $\setminus$ C & refcat-doi only & 256,985,697 \\ % xxx 295,884,246 + COCIv11 (C) & & 1,186,958,897 \\ % zstdcat -T0 6741422v11.csv.zst | pv -l | wc -l + \emph{refcat-doi} (R) & & 1,303,424,212 \\ % zstdcat -T0 /magna/refcat/2021-07-28/BrefDOITable/date-2021-07-28.tsv.zst | pv -l | LC_ALL=C sort -T /sandcrawler-db/tmp-refcat/ -S70% -k3,4 -u | zstd -c -T0 > uniq_34.tsv.zst # LC_ALL=C wc -l uniq_34_doi_lower_sorted.csv + C $\cap$ R & overlap & 1,046,438,515 \\ + C $\setminus$ R & COCIv11 only & 140,520,382 \\ % 86,854,309 \\ + R $\setminus$ C & \emph{refcat-doi} only & 256,985,697 \\ % xxx 295,884,246 \end{tabular} \vspace*{2mm} \caption{Comparison between Open Citations COCI corpus (v11, @@ -270,11 +271,11 @@ web links\footnote{The cleaning process is necessary because OCR artifacts and reference corpus, of which 4,828,283 (19\%) have been preserved as of August 2021 with an HTTP 200 status code in the Wayback Machine\footnote{\href{https://archive.org/web/}{https://archive.org/web/}} of -the Internet Archive. As an upper bound - if we include all redirection (HTTP -3XX) and server error status code (HTTP 5XX) - we find a total of 14,306,019 (56.3\%) links preserved. +the Internet Archive. As an upper bound - if we additionally include all redirection (HTTP +3XX) and server error status codes (HTTP 5XX) - we find a total of 14,306,019 (56.3\%) links preserved. -We ran a live URL check over a sample of 364415 links found in the reference -corpus. Of the 364415 links we find 305476 (83.8\%) responding with an HTTP +We ran a live URL check\footnote{All links accessed on 2021-10-04 and 2021-10-05.} over a sample of 364415 links which appear in the reference +corpus \emph{and} have a HTTP 200 status code archival copy in the Wayback Machine. Of the 364415 links we find 305476 (83.8\%) responding with an HTTP 200 OK, whereas the rest of the links yield a variety of HTTP status codes, like 404, 403, 500 and others - resulting in about 16\% of the links in the reference corpus preserved at the Internet Archive being currently inaccessible @@ -447,8 +448,9 @@ This work is partially supported by grants from the \emph{Andrew W. Mellon Foundation}, especially ''Ensuring the Persistent Access of Open Access Journal Literature: Phase II`` (1910-07256, Jefferson Bailey, Principal Investigator). +\appendix -\section{Appendix A} +\section*{Appendix: Reference Relations} Figure~\ref{fig:types} shows the schematic reference relations. @@ -461,7 +463,9 @@ Figure~\ref{fig:types} shows the schematic reference relations. \label{fig:types} \end{figure} -\section{Appendix B} +% \pagebreak{} + +\section*{Appendix: Data Quality} A note on data quality: While we implement various data quality measures, @@ -470,7 +474,7 @@ issues. Among other measures, we keep track of match reasons, especially for fuzzy matching to be able to zoom in on systematic errors more easily (see~Table~\ref{table:matches}). -\begin{table}[] +\begin{table}[H] \footnotesize \captionsetup{font=normalsize} \begin{center} -- cgit v1.2.3