%APN3_PROCEEDINGS_FORM%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
% TEMPLATE.TEX -- APN3 (2003) ASP Conference Proceedings template.
%
% Derived from ADASS VIII (98) ASP Conference Proceedings template
% Updated by N. Manset for ADASS IX (99), F. Primini for ADASS 2000,
% D.Bohlender for ADASS 2001, and H. Payne for ADASS XII and LaTeX2e.
%
% Use this template to create your proceedings paper in LaTeX format
% by following the instructions given below.  Much of the input will
% be enclosed by braces (i.e., { }).  The percent sign, "%", denotes
% the start of a comment; text after it will be ignored by LaTeX.  
% You might also notice in some of the examples below the use of "\ "
% after a period; this prevents LaTeX from interpreting the period as
% the end of a sentence and putting extra space after it.  
% 
% You should check your paper by processing it with LaTeX.  For
% details about how to run LaTeX as well as how to print out the User
% Guide, consult the README file.  You should also consult the sample
% LaTeX papers, sample1.tex and sample2.tex, for examples of including
% figures, html links, special symbols, and other advanced features.
%
% If you do not have access to the LaTeX software or a laser printer
% at your site, you can still prepare your paper following the
% instructions in the User Guide.  In such cases, the editors will
% process the file and make any necessary editorial adjustments.
% 
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% 
\documentclass[11pt,twoside]{article}  % Leave intact
\usepackage{adassconf}

% If you have the old LaTeX 2.09, and not the current LaTeX2e, comment
% out the \documentclass and \usepackage lines above and uncomment
% the following:

%\documentstyle[11pt,twoside,adassconf]{article}

\begin{document}   % Leave intact

%-----------------------------------------------------------------------
%			    Paper ID Code
%-----------------------------------------------------------------------
% Enter the proper paper identification code.  The ID code for your
% paper is the session number associated with your presentation as
% published in the official conference proceedings.  You can           
% find this number locating your abstract in the printed proceedings
% that you received at the meeting or on-line at the conference web
% site; the ID code is the letter/number sequence proceeding the title 
% of your presentation. 
%
% This will not appear in your paper; however, it allows different
% papers in the proceedings to cross-reference each other.  Note that
% you should only have one \paperID, and it should not include a
% trailing period.
%
% EXAMPLE: \paperID{O4-1}
% EXAMPLE: \paperID{P7-7}
%

\paperID{O7-6}
%%%% ID=O7-6

%-----------------------------------------------------------------------
%		            Paper Title 
%-----------------------------------------------------------------------
% Enter the title of the paper.
%
% EXAMPLE: \title{A Breakthrough in Astronomical Software Development}
% 
% If your title is so long as to fill the page header when you print it,
% then please supply a short form as a \titlemark.
%
% EXAMPLE: 
%  \title{Rapid Development for Distributed Computing, with Implications
%         for the Virtual Observatory}
%  \titlemark{Rapid Development for Distributed Computing}
%

\title{The Chandra Bibliography Database }
%\titlemark{ }

%-----------------------------------------------------------------------
%		          Authors of Paper
%-----------------------------------------------------------------------
% Enter the authors followed by their affiliations.  The \author and
% \affil commands may appear multiple times as necessary (see example
% below).  List each author by giving the first name or initials first
% followed by the last name.  Authors with the same affiliations
% should grouped together. 
%
% EXAMPLE: \author{Raymond Plante, Doug Roberts, 
%                  R.\ M.\ Crutcher\altaffilmark{1}}
%          \affil{National Center for Supercomputing Applications, 
%                 University of Illinois Urbana-Champaign, Urbana, IL
%                 61801}
%          \author{Tom Troland}
%          \affil{University of Kentucky}
%
%          \altaffiltext{1}{Astronomy Department, UIUC}
%
% In this example, the first three authors, "Plante", "Roberts", and
% "Crutcher" are affiliated with "NCSA".  "Crutcher" has an alternate 
% affiliation with the "Astronomy Department".  The fourth author,
% "Troland", is affiliated with "University of Kentucky"

\author{Arnold H.\ Rots, Sherry L.\ Winkelman, Sarah E.\ Blecksmith,
John D.\ Bright}
\affil{Harvard-Smithsonian Center for Astrophysics, 60 Garden Street
MS 67, Cambridge, MA 02138, U.S.A.}
\author{St\'{e}phane Paltani}
\affil{Observatoire de Marseille}

%-----------------------------------------------------------------------
%			 Contact Information
%-----------------------------------------------------------------------
% This information will not appear in the paper but will be used by
% the editors in case you need to be contacted concerning your
% submission.  Enter your name as the contact along with your email
% address.
% 
% EXAMPLE:  \contact{Dennis Crabtree}
%           \email{crabtree@cfht.hawaii.edu}
%

\contact{Arnold Rots}
\email{arots@head.cfa.harvard.edu}

%-----------------------------------------------------------------------
%		      Author Index Specification
%-----------------------------------------------------------------------
% Specify how each author name should appear in the author index.  The 
% \paindex{ } should be used to indicate the primary author, and the
% \aindex for all other co-authors.  You MUST use the following
% syntax: 
%
% SYNTAX:  \aindex{Lastname, F. M.}
% 
% where F is the first initial and M is the second initial (if
% used).  This guarantees that authors that appear in multiple papers
% will appear only once in the author index.  
%
% EXAMPLE: \paindex{Crabtree, D.}
%          \aindex{Manset, N.}        
%          \aindex{Veillet, C.}        
%
% NOTE: this information is also used to build the author list that
% appears in the table of contents.  Authors will be listed in the order
% of the \paindex and \aindex commmands.
%

\paindex{Rots, A.}
\aindex{Winkelman, S.}
\aindex{Paltani, S.}
\aindex{Blecksmith, S.}
\aindex{Bright, J. D.}

%-----------------------------------------------------------------------
%		      Author list for page header	
%-----------------------------------------------------------------------
% Please supply a list of author last names for the page header. in
% one of these formats:
%
% EXAMPLES:
% \authormark{Lastname}
% \authormark{Lastname1 \& Lastname2}
% \authormark{Lastname1, Lastname2, ... \& LastnameN}
% \authormark{Lastname et al.}
%
% Use the "et al." form in the case of seven or more authors, or if
% the preferred form is too long to fit in the header.

\authormark{Rots, Winkelman, Blecksmith, Bright \& Paltani}

%-----------------------------------------------------------------------
%			Subject Index keywords
%-----------------------------------------------------------------------
% Enter a comma separated list of up to 6 keywords describing your
% paper.  These will NOT be printed as part of your paper; however,
% they will be used to generate the subject index for the proceedings.
% There is no standard list; however, you can consult the indices
% for past proceedings (http://adass.org/adass/proceedings/).
%
% EXAMPLE:  \keywords{visualization, astronomy: radio, parallel
%                     computing, AIPS++, Galactic Center}
%
% In this example, the author noticed that "radio astronomy" appeared
% in the ADASS VII Index as "astronomy" being the major keyword and
% "radio" as the minor keyword.  The colon is used to introduce another
% level into the index.

\keywords{archives, databases: bibliographic, archives: interoperability}

%-----------------------------------------------------------------------
%			       Abstract
%-----------------------------------------------------------------------
% Type abstract in the space below.  Consult the User Guide and Latex
% Information file for a list of supported macros (e.g. for typesetting 
% special symbols). Do not leave a blank line between \begin{abstract} 
% and the start of your text.

\begin{abstract}          % Leave intact
% Place the text of your abstract here - NO BLANK LINES
Early in the mission, the Chandra Data Archive started the development of a
bibliography database, tracking publications in refereed journals and
on-line conference proceedings that are based on Chandra observations,
allowing our users to link directly to articles in the ADS from our
archive, and to link to the relevant data in the archive from the ADS
entries.  Subsequently, we have been working closely with the ADS and
other data centers, in the context of the ADEC-ITWG, on standardizing
the literature-data linking.  We have also extended our bibliography
database to include all Chandra-related articles and we are also
keeping track of the number of citations of
each paper.  Obviously, in addition to providing valuable services to
our users, this database allows us to extract a wide variety of
statistical information.
The project comprises five components: the bibliography database-proper,
a maintenance database, an interactive maintenance tool, a user
browsing interface, and a web services component for exchanging
information with the ADS.  All of these elements are nearly
mission-independent and we intend make the package as a whole
available for use by other data centers.  The capabilities thus
provided represent support for an essential component of the Virtual
Observatory.

\end{abstract}

%-----------------------------------------------------------------------
%			      Main Body
%-----------------------------------------------------------------------
% Place the text for the main body of the paper here.  You should use
% the \section command to label the various sections; use of
% \subsection is optional.  Significant words in section titles should
% be capitalized.  Sections and subsections will be numbered
% automatically. 
%
% EXAMPLE:  \section{Introduction}
%           ...
%           \subsection{Our View of the World}
%           ...
%           \section{A New Approach}
%
% It is recommended that you look at the sample papers, sample1.tex
% and sample2.tex, for examples for formatting references, footnotes,
% figures, equations, html links, lists, and other special features.  

\section{Introduction and Existing Capabilities}
For the past two years the Chandra Data Archive
(\htmladdnormallinkfoot{CDA}{http://cxc.harvard.edu/cda}) has been
building a database linking articles in the literature to Chandra
datasets being presented in those articles as a service to our own
users and to users of the
\htmladdnormallinkfoot{ADS}{http://adswww.harvard.edu/}.

Currently, on the side of the CDA users are
able to link from observations to articles in the ADS, while there
are also some links to scattered publications.  On the part of the
ADS, users can link from articles presenting Chandra observations to
those datasets in the archive and select articles with general Chandra
mission tags.

These are valuable services but not as general as one would like and
very labor-intensive to maintain: to date humans have inspected 11,000
articles to be judged on relevance and manually made 2400 links between
the literature and the archive's datasets.  The objective is to move
to a system where the links can be harvested automatically and users
are provided with access to data and published articles through the
ADS and through the data centers as illustrated in Fig.\ 1.  We will
outline in the following sections the steps that will lead to such
improved user-friendliness.

\begin{figure}
%\epsscale{.80}
\plotone{O7-6bibli.eps}
\caption{Planned query mechanisms to allow users flexible access to
data and publications.} \label{O7.6-fig-1}
\end{figure}


\section{Identifiers and Automatic Linking}
The ADS, the data centers, and the US journal editors are working on a
proposed agreement that will enable authors to insert links to
archived datasets directly into their manuscripts.  These identifiers
will be IVOA (International Virtual Observatory Alliance) compliant
and consist of a name space (ivo:), an authority Id (ADS), a data
collection (e.g., Sa.CXO), and a dataset name.  For more detailed
information, see Accomazzi \& Eichhorn (2004).

The objective is to allow the data centers and the ADS to harvest the
links between the literature and the archived datasets automatically,
thus eliminating a large component of the labor that is currently
invested in bibliographic databases associated with archives.


\section{Database Extension}
Whereas our database originally only contained links between datasets
and the bibcodes of journal articles and conference proceeding papers
that presented these datasets, we have been extending it in three
directions.  First, we now include five subject categories of papers:
referring to specific observations (the original database); referring
to published results; predicting Chandra results; referring to
instrumentation, software, or operations; other.  Second, we now
include all other types of publications, with the exception of
preprints.  We would be prepared to include Astro-ph articles if the
data identifier links could be harvested from that site; but it does
not seem likely that this will happen anytime soon.  Third, we are
including a large variety of of attributes for each article in our
database, such as: subject category; kind of publication (book,
journal, proceedings, thesis, circular, review, newsletter, internal
note); type of publication (article, abstract, memo, data, erratum,
title only, electronic); number of citations; keywords; date of
publication; refereed or not.

To this end we have expanded our database to 10 tables:
\begin{itemize}
\item {\bf BibTable} is the main table that holds one record for each
article with all simple attributes, some of them encoded.
\item {\bf ObsId} contains the links between bibcodes and single-observation
datasets.  Each
ObsId may refer to more than one record in the BibTable and each
record in the BibTable may refer to more than one ObsId record.
ObsIds link to the observation catalog (a separate database) and to
proposals for more information.
\item {\bf Subjects} contains the description of the five encoded subject
categories.
\item {\bf Datasets} are conglomerates of observations that belong together
and are represented by a single identifier, rather than (potentially)
a large number of identifiers.
\item {\bf DatasetObsIds} enumerates the ObsIds contained in each Datasets
record.
\item {\bf URLs} provides a mapping between BibTable entries and articles
that are maintained as specific URLs.
\item {\bf StdKeywords} contains the standard keywords for each article.
\item {\bf StdKeywordCategories} holds the descriptions of the standard
journal keyword categories.
\item {\bf StdKeywordList} is the list of canonical standard keywords as
adopted by the major journals.
\item {\bf CustomKeywords} holds the keywords invented by individual
authors.
\end{itemize}


\noindent 	%% FO
We manage the entry of new records into the bibliography database
through a dedicated database which is filled through automated queries
to the ADS database. Attributes are filled in through a GUI and the
entries are migrated to BibTable upon completion.

In addition, automated ADS queries update the number of citations for
each article and check the continued validity of all bibcodes.


Table 1 provides some statistics on our database as of ADASS XIII.

\begin{deluxetable}{lrrrrrrr}
\tablecaption{Number of articles in the CDA bibliography database as
of early October 2003}
\tablehead{
\colhead{Category} &
\colhead{1999} &
\colhead{2000} &
\colhead{2001} &
\colhead{2002} &
\colhead{2003} &
\colhead{Total} &
\colhead{No.\ Cit.} }

\startdata
Observations & 53 & 284 & 485 & 485 & 352 & 1659 & 5639\\
Refer to obs. & 9 &  94 & 333 & 499 & 322 & 1257 & 5300\\
Instr., s/w, ops. & 34 & 141 & 124 &  69 &  18 &  386 & 1362\\
Predict result & 11 & 67 & 21 &  14 &  21 &  135 &  306\\
Unclassified & 15 &  90 &  70 &  29 &  40 &  244 &  663\\
Total     &   122 & 676 &1033 &1097 & 753 & 3681 &13270\\
Total Reviewed&1011&2507&2735 &2758 &1859 &10870\\
\enddata

\end{deluxetable}


\section{Services}
We are developing the following services:
\begin{itemize}
\item Exchange of information with the ADS, in particular the
harvesting of Bibcode-Dataset Identifier pairs in both directions.
\item Provide access to datasets through either a Dataset Identifier
or a Bibcode.
\item Provide information to the ADS on Bibcodes that are not related
to specific observations.
\item Provide access to publications through queries from our
archive. We are developing a specialized literature query interface
related to the Chandra mission, allowing users to search for articles
on the basis of criteria that are specific to Chandra.
\item Derive metrics through queries to the bibliography database
(standardized metrics as well as custom requests).
\end{itemize}


\section{Conclusion}
We have developed a comprehensive database design that is capable of
tracking almost all mission-related publications and preserving all
relevant information.  Added to this are a database and GUI that make
maintenance, particularly data entry, as painless as possible.  Our
services include cross-linking with the ADS, literature search
from our archive, and metrics.

The entire package is reasonably mission-independent and available to
other data centers.


\begin{acknowledgements}
This work is supported by NASA contract NAS 8-39073 (CXC).


\end{acknowledgements}

%-----------------------------------------------------------------------
%			      References
%-----------------------------------------------------------------------
% List your references below within the reference environment
% (i.e. between the \begin{references} and \end{references} tags).
% Each new reference should begin with a \reference command which sets
% up the proper indentation.  Observe the following order when listing
% bibliographical information for each reference:  author name(s),
% publication year, journal name, volume, and page number for
% articles.  Note that many journal names are available as macros; see
% the User Guide listing "macro-ized" journals.   
%
% EXAMPLE:  \reference Hagiwara, K., \& Zeppenfeld, D.\  1986, 
%                Nucl.Phys., 274, 1
%           \reference H\'enon, M.\  1961, Ann.d'Ap., 24, 369
%           \reference King, I.\ R.\  1966, \aj, 71, 276
%           \reference King, I.\ R.\  1975, in Dynamics of Stellar 
%                Systems, ed.\ A.\ Hayli (Dordrecht: Reidel), 99
%           \reference Tody, D.\  1998, \adassvii, 146
%           \reference Zacharias, N.\ \& Zacharias, M.\ 2003,
%                \adassxii, \paperref{P7.6}
% 
% Note the following tricks used in the example above:
%
%   o  \& is used to format an ampersand symbol (&).
%   o  \'e puts an accent agu over the letter e.  See the User Guide
%      and the sample files for details on formatting special
%      characters.  
%   o  "\ " after a period prevents LaTeX from interpreting the period 
%      as an end of a sentence.
%   o  \aj is a macro that expands to "Astron. J."  See the User Guide
%      for a full list of journal macros
%   o  \adassvii is a macro that expands to the full title, editor,
%      and publishing information for the ADASS VII conference
%      proceedings.  Such macros are defined for ADASS conferences I
%      through XI.
%   o  When referencing a paper in the current volume, use the
%      \adassxii and \paperref macros.  The argument to \paperref is
%      the paper ID code for the paper you are referencing.  See the 
%      note in the "Paper ID Code" section above for details on how to 
%      determine the paper ID code for the paper you reference.  
%
\begin{references}

\reference Accomazzi, A.\ \& Eichhorn, G.\ 
    2004, \adassxiii, \paperref{P2-20}


\end{references}

% Do not place any material after the references section

\end{document}  % Leave intact