{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24a8a48858fbf4a696cb1d3768679a468/katharinafuchs", "tags" : [ "pebble","peerReviewed","pn7","ipvs-de","from:m.herschel","EXC2075" ], "intraHash" : "4a8a48858fbf4a696cb1d3768679a468", "interHash" : "c4090f2bbe6977741516fff15b794a1f", "label" : "Distributed Tree-Pattern Matching in Big Data Analytics Systems", "user" : "katharinafuchs", "description" : "", "date" : "2021-12-08 17:10:08", "changeDate" : "2021-12-08 16:10:08", "count" : 6, "pub-type": "inproceedings", "booktitle": "In Proceedings of the Conference on Advances in Databases and Information Systems (ADBIS)","series": "Lecture Notes in Computer Science","publisher":"Springer", "year": "2020", "url": "", "author": [ "Ralf Diestelkämper","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"} ], "pages": "171-186", "doi" : "https://doi.org/10.1007/978-3-030-54832-2_14", "bibtexKey": "DBLP:conf/adbis/DiestelkamperH20" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2cd8061bce8aa1569289c8387816f7998/katharinafuchs", "tags" : [ "pebble","provenance","peerReviewed","pn7","ipvs-de","from:m.herschel","EXC2075" ], "intraHash" : "cd8061bce8aa1569289c8387816f7998", "interHash" : "60303345861e8a5ec1846d6d36028b19", "label" : "Tracing nested data with structural provenance for big data analytics", "user" : "katharinafuchs", "description" : "", "date" : "2021-12-08 17:10:08", "changeDate" : "2021-12-08 16:10:08", "count" : 6, "pub-type": "inproceedings", "booktitle": "Proceedings of the International Conference on Extending Database Technology (EDBT)", "year": "2020", "url": "https://doi.org/10.5441/002/edbt.2020.23", "author": [ "Ralf Diestelkämper","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"} ], "pages": "253-264", "bibsource" : "dblp computer science bibliography, https://dblp.org", "doi" : "10.5441/002/edbt.2020.23", "bibtexKey": "DBLP:conf/edbt/DiestelkamperH20" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/257caa64fbf43b0c44f8988853da3281b/katharinafuchs", "tags" : [ "pebble","why-not","peerReviewed","pn7","ipvs-de","from:m.herschel","EXC2075" ], "intraHash" : "57caa64fbf43b0c44f8988853da3281b", "interHash" : "6e76c5cda24e1e87e3924ae022a4bfa2", "label" : "To not miss the forest for the trees - A holistic approach for explaining missing answers over nested data", "user" : "katharinafuchs", "description" : "", "date" : "2021-12-08 17:10:08", "changeDate" : "2021-12-08 16:10:08", "count" : 6, "pub-type": "inproceedings", "booktitle": "In Proceedins of the ACM SIG Conference on the Management of Data (SIGMOD)", "year": "2021", "url": "", "author": [ "Ralf Diestelkämper","Seokki Lee","Melanie Herschel","Boris Glavic" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Seokki", "last" : "Lee"}, {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Boris", "last" : "Glavic"} ], "bibtexKey": "diestelkamper2021forest" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/257caa64fbf43b0c44f8988853da3281b/m.herschel", "tags" : [ "pebble","why-not","peerReviewed","pn7","ipvs-de","EXC2075" ], "intraHash" : "57caa64fbf43b0c44f8988853da3281b", "interHash" : "6e76c5cda24e1e87e3924ae022a4bfa2", "label" : "To not miss the forest for the trees - A holistic approach for explaining missing answers over nested data", "user" : "m.herschel", "description" : "", "date" : "2021-07-01 02:43:31", "changeDate" : "2023-10-16 14:39:34", "count" : 6, "pub-type": "inproceedings", "booktitle": "In Proceedins of the ACM SIG Conference on the Management of Data (SIGMOD)", "year": "2021", "url": "https://dl.acm.org/doi/pdf/10.1145/3448016.3457249", "author": [ "Ralf Diestelkämper","Seokki Lee","Melanie Herschel","Boris Glavic" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Seokki", "last" : "Lee"}, {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Boris", "last" : "Glavic"} ], "bibtexKey": "diestelkamper2021forest" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/280b83869bafaaedcefd3d8193380ef7e/m.herschel", "tags" : [ "pebble","why-not","peer","ipvs-de","rp9" ], "intraHash" : "80b83869bafaaedcefd3d8193380ef7e", "interHash" : "eb99783d7f6b252331bb157c5975e957", "label" : "Debugging Missing Answers for Spark Queries over Nested Data with Breadcrumb", "user" : "m.herschel", "description" : "", "date" : "2021-07-01 02:39:02", "changeDate" : "2023-01-10 13:07:17", "count" : 2, "pub-type": "article", "journal": "Proceedings of the VLDB Endowment (PVLDB)", "year": "2021", "url": "http://www.vldb.org/pvldb/vol14/p2731-diestelkamper.pdf", "author": [ "Ralf Diestelkamper","Seokki Lee","Boris Glavic","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkamper"}, {"first" : "Seokki", "last" : "Lee"}, {"first" : "Boris", "last" : "Glavic"}, {"first" : "Melanie", "last" : "Herschel"} ], "bibtexKey": "diestelkamper2021debugging" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/27b78bd3729e1ba8acf0505472ba75669/m.herschel", "tags" : [ "pebble","d03","ipvs-de","trr161" ], "intraHash" : "7b78bd3729e1ba8acf0505472ba75669", "interHash" : "a8acf1ec91c81df66b5c3a657f0dbd4b", "label" : "A survey on provenance: What for? What form? What from?", "user" : "m.herschel", "description" : "", "date" : "2021-03-15 10:08:22", "changeDate" : "2023-01-04 14:39:21", "count" : 15, "pub-type": "article", "journal": "The VLDB Journal", "year": "2017", "url": "https://www.ipvs.uni-stuttgart.de/departments/de/resources/papers/provenance_survey_online.pdf", "author": [ "Melanie Herschel","Ralf Diestelkämper","Houssem Ben Lahmar" ], "authors": [ {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Houssem", "last" : "Ben Lahmar"} ], "volume": "26","number": "6","pages": "881-906", "bibsource" : "dblp computer science bibliography, https://dblp.org", "doi" : "10.1007/s00778-017-0486-1", "bibtexKey": "herschel2017survey" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24a8a48858fbf4a696cb1d3768679a468/m.herschel", "tags" : [ "pebble","peerReviewed","pn7","ipvs-de","EXC2075" ], "intraHash" : "4a8a48858fbf4a696cb1d3768679a468", "interHash" : "c4090f2bbe6977741516fff15b794a1f", "label" : "Distributed Tree-Pattern Matching in Big Data Analytics Systems", "user" : "m.herschel", "description" : "", "date" : "2020-10-06 12:08:22", "changeDate" : "2023-10-16 14:41:16", "count" : 6, "pub-type": "inproceedings", "booktitle": "In Proceedings of the Conference on Advances in Databases and Information Systems (ADBIS)","series": "Lecture Notes in Computer Science","publisher":"Springer", "year": "2020", "url": "", "author": [ "Ralf Diestelkämper","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"} ], "pages": "171-186", "doi" : "https://doi.org/10.1007/978-3-030-54832-2_14", "bibtexKey": "DBLP:conf/adbis/DiestelkamperH20" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2c6526c31eb0a5a9fcb618b5a5eb85084/m.herschel", "tags" : [ "pebble","why-not","ipvs-de" ], "intraHash" : "c6526c31eb0a5a9fcb618b5a5eb85084", "interHash" : "964bd6691905ac81282708dc30c9c534", "label" : "Query-based Why-not Explanations for Nested Data", "user" : "m.herschel", "description" : "", "date" : "2020-03-26 10:02:25", "changeDate" : "2021-03-15 07:38:15", "count" : 1, "pub-type": "inproceedings", "booktitle": "Proceedings of the International Workshop on Theory and Practice of Provenance (TaPP)","publisher":"USENIX Association", "year": "2019", "url": "https://www.usenix.org/conference/tapp2019/presentation/diestelkamper", "author": [ "Ralf Diestelkämper","Boris Glavic","Melanie Herschel","Seokki Lee" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Boris", "last" : "Glavic"}, {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Seokki", "last" : "Lee"} ], "bibtexKey": "diestelkamper2019querybased" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24842540bfb78d745c0cc523661b787db/m.herschel", "tags" : [ "pebble","ipvs-de" ], "intraHash" : "4842540bfb78d745c0cc523661b787db", "interHash" : "f3d537df79e4eec822ed6987aa0fe655", "label" : "Provenance in DISC Systems: Reducing Space Overhead at Runtime", "user" : "m.herschel", "description" : "", "date" : "2020-03-26 09:59:23", "changeDate" : "2020-10-22 12:55:00", "count" : 10, "pub-type": "inproceedings", "booktitle": "Proceedings of the USENIX Conference on Theory and Practice of Provenance (TAPP)", "year": "2017", "url": "https://dl.acm.org/doi/abs/10.5555/3183865.3183883", "author": [ "Ralf Diestelkämper","Melanie Herschel","Priyanka Jadhav" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Priyanka", "last" : "Jadhav"} ], "pages": "1-13","abstract": "Data intensive scalable computing (DISC) systems, such asApache Hadoop or Spark, allow to process large amountsof heterogenous data. For varying provenance applications,emerging provenance solutions for DISC systems track allsource data items through each processing step, imposing ahigh space and time overhead during program execution.We introduce a provenance collection approach that re-duces the space overhead at runtime by sampling the inputdata based on the definition of equivalence classes. A pre-liminary empirical evaluation shows that this approach al-lows to satisfy many use cases of provenance applications indebugging and data exploration, indicating that provenancecollection for a fraction of the input data items often suf-fices for selected provenance applications. When additionalprovenance is required, we further outline a method to col-lect provenance at query time, reusing, when possible, par-tial provenance already collected during program execution", "bibtexKey": "diestelkamper2017provenance" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2e931977230f6563fbbced0fa9ca8d421/m.herschel", "tags" : [ "pebble","ivps-de","vldbj","d03","trr161" ], "intraHash" : "e931977230f6563fbbced0fa9ca8d421", "interHash" : "a8acf1ec91c81df66b5c3a657f0dbd4b", "label" : "A Survey on Provenance - What for? What form? What from?", "user" : "m.herschel", "description" : "", "date" : "2020-03-26 09:57:54", "changeDate" : "2021-03-15 09:04:09", "count" : 15, "pub-type": "article", "journal": "The VLDB Journal", "year": "2017", "url": "https://doi.org/10.1007/s00778-017-0486-1", "author": [ "Melanie Herschel","Ralf Diestelkämper","Houssem Ben Lahmar" ], "authors": [ {"first" : "Melanie", "last" : "Herschel"}, {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Houssem", "last" : "Ben Lahmar"} ], "volume": "26","pages": "881-906","abstract": "Provenance refers to any information describing the production process of an end product, which can be anything from a piece of digital data to a physical object. While this survey focuses on the former type of end product, this definition still leaves room for many different interpretations of and approaches to provenance. These are typically motivated by different application domains for provenance (e.g., accountability, reproducibility, process debugging) and varying technical requirements such as runtime, scalability, or privacy. As a result, we observe a wide variety of provenance types and provenance-generating methods. This survey provides an overview of the research field of provenance, focusing on what provenance is used for (what for?), what types of provenance have been defined and captured for the different applications (what form?), and which resources and system requirements impact the choice of deploying a particular provenance solution (what from?). For each of these three key questions, we provide a classification and review the state of the art for each class. We conclude with a summary and possible future research challenges.", "doi" : "10.1007/s00778-017-0486-1", "bibtexKey": "herschel2017survey" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/28c5e63061b23aaf628a1a953893a4a8c/m.herschel", "tags" : [ "pebble","peer","d03","ipvs-de","trr161","rp9" ], "intraHash" : "8c5e63061b23aaf628a1a953893a4a8c", "interHash" : "b35f83138eea50ec98f8a106d1f3a677", "label" : "Capturing and Querying Structural Provenance in Spark with Pebble", "user" : "m.herschel", "description" : "", "date" : "2020-03-26 09:53:44", "changeDate" : "2021-03-15 07:41:40", "count" : 4, "pub-type": "inproceedings", "booktitle": "In ACM International Conference on Management of Data (SIGMOD)", "year": "2019", "url": "https://doi.org/10.1145/3299869.3320225", "author": [ "Ralf Diestelkämper","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"} ], "pages": "1893-1896", "ee" : "https://doi.org/10.1145/3299869.3320225", "bibtexKey": "diestelkmper2019capturing" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2cd8061bce8aa1569289c8387816f7998/m.herschel", "tags" : [ "pebble","provenance","peerReviewed","pn7","ipvs-de","EXC2075" ], "intraHash" : "cd8061bce8aa1569289c8387816f7998", "interHash" : "60303345861e8a5ec1846d6d36028b19", "label" : "Tracing nested data with structural provenance for big data analytics", "user" : "m.herschel", "description" : "", "date" : "2020-03-26 09:31:39", "changeDate" : "2023-10-16 14:42:27", "count" : 6, "pub-type": "inproceedings", "booktitle": "Proceedings of the International Conference on Extending Database Technology (EDBT)", "year": "2020", "url": "https://doi.org/10.5441/002/edbt.2020.23", "author": [ "Ralf Diestelkämper","Melanie Herschel" ], "authors": [ {"first" : "Ralf", "last" : "Diestelkämper"}, {"first" : "Melanie", "last" : "Herschel"} ], "pages": "253-264", "bibsource" : "dblp computer science bibliography, https://dblp.org", "bibtexKey": "diestelkmper2020tracing" } ] }