{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/data-integration/papers/5","list_of":"/task/data-integration","task":"Data Integration","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,431],"of":431,"counts":{"archive_papers_tagged":431,"with_a_code_link":130,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":431,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/data-integration","prev":"/task/data-integration/papers/4","next":null,"papers":[{"url":null,"slug":"hybrid-modelling-in-oncology-sucesses","title":"Hybrid Modelling in Oncology: Sucesses, Challenges and Hopes","date":"2019-01-17","arxiv_id":"1901.05652","repositories_listed":0,"syntology":null},{"url":null,"slug":"tweetskb-a-public-and-large-scale-rdf-corpus","title":"TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets","date":"2018-10-23","arxiv_id":"1810.10308","repositories_listed":0,"syntology":null},{"url":null,"slug":"reuse-and-adaptation-for-entity-resolution","title":"Reuse and Adaptation for Entity Resolution through Transfer Learning","date":"2018-09-28","arxiv_id":"1809.11084","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-for-integrating-data-in","title":"Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities","date":"2018-06-30","arxiv_id":"1807.00123","repositories_listed":0,"syntology":null},{"url":null,"slug":"specifying-monitoring-and-executing-workflows","title":"Specifying, Monitoring, and Executing Workflows in Linked Data Environments","date":"2018-04-13","arxiv_id":"1804.05044","repositories_listed":0,"syntology":null},{"url":null,"slug":"k-shell-decomposition-reveals-hierarchical","title":"K-shell decomposition reveals hierarchical cortical organization of the human brain","date":"2018-03-10","arxiv_id":"1803.03742","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-joint-matrix-decomposition-for-data","title":"Bayesian Joint Matrix Decomposition for Data Integration with Heterogeneous Noise","date":"2017-12-09","arxiv_id":"1712.03337","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-vision-for-health-informatics-introducing","title":"A Vision for Health Informatics: Introducing the SKED Framework.An Extensible Architecture for Scientific Knowledge Extraction from Data","date":"2017-06-24","arxiv_id":"1706.07992","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-accurate-drought-forecasting","title":"A Framework for Accurate Drought Forecasting System Using Semantics-Based Data Integration Middleware","date":"2017-06-20","arxiv_id":"1706.07294","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effects-of-alternative-optima-in","title":"On the effects of alternative optima in context-specific metabolic model predictions","date":"2017-06-15","arxiv_id":"1610.06240","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-kernel-ls-svm-based-bio-clinical-data","title":"Multi-Kernel LS-SVM Based Bio-Clinical Data Integration: Applications to Ovarian Cancer","date":"2017-04-10","arxiv_id":"1704.02846","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multiple-kernel-principal-component","title":"Towards multiple kernel principal component analysis for integrative analysis of tumor samples","date":"2017-01-02","arxiv_id":"1701.00422","repositories_listed":0,"syntology":null},{"url":null,"slug":"ncbo-ontology-recommender-20-an-enhanced","title":"NCBO Ontology Recommender 2.0: An Enhanced Approach for Biomedical Ontology Recommendation","date":"2016-11-18","arxiv_id":"1611.05973","repositories_listed":0,"syntology":null},{"url":null,"slug":"anfrage-getriebener-wissenstransfer-zur","title":"Anfrage-getriebener Wissenstransfer zur Unterstuetzung von Datenanalysten","date":"2016-10-20","arxiv_id":"1610.06382","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-analyzer-for-the-comprehension-of","title":"A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech","date":"2016-10-08","arxiv_id":"1610.02493","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-integration-with-high-dimensionality","title":"Data Integration with High Dimensionality","date":"2016-10-03","arxiv_id":"1610.00667","repositories_listed":0,"syntology":null},{"url":null,"slug":"drug-response-prediction-by-inferring-pathway","title":"Drug response prediction by inferring pathway-response associations with Kernelized Bayesian Matrix Factorization","date":"2016-06-11","arxiv_id":"1606.03623","repositories_listed":0,"syntology":null},{"url":null,"slug":"acceleration-of-deep-neural-network-training","title":"Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices","date":"2016-03-23","arxiv_id":"1603.07341","repositories_listed":0,"syntology":null},{"url":null,"slug":"git4voc-git-based-versioning-for","title":"Git4Voc: Git-based Versioning for Collaborative Vocabulary Development","date":"2016-01-11","arxiv_id":"1601.02433","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-exome-and-gene-expression-datasets","title":"Combining exome and gene expression datasets in one graphical model of disease to empower the discovery of disease mechanisms","date":"2015-08-30","arxiv_id":"1508.07527","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-matrix-completion-with","title":"Structured Matrix Completion with Applications to Genomic Data Integration","date":"2015-04-08","arxiv_id":"1504.01823","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-equivalence-and-oid-equivalence-of","title":"Mapping-equivalence and oid-equivalence of single-function object-creating conjunctive queries","date":"2015-03-05","arxiv_id":"1503.01707","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-analytics-in-mom-applications","title":"Context-Aware Analytics in MOM Applications","date":"2014-12-26","arxiv_id":"1412.7968","repositories_listed":0,"syntology":null},{"url":null,"slug":"equinmf-graph-regularized-multiview","title":"EquiNMF: Graph Regularized Multiview Nonnegative Matrix Factorization","date":"2014-09-14","arxiv_id":"1409.4018","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-machine-compiled-macroevolutionary-history","title":"A machine-compiled macroevolutionary history of Phanerozoic life","date":"2014-06-11","arxiv_id":"1406.2963","repositories_listed":0,"syntology":null},{"url":null,"slug":"principled-graph-matching-algorithms-for","title":"Principled Graph Matching Algorithms for Integrating Multiple Data Sources","date":"2014-02-03","arxiv_id":"1402.0282","repositories_listed":0,"syntology":null},{"url":null,"slug":"hino-a-bfo-aligned-ontology-representing","title":"HINO: a BFO-aligned ontology representing human molecular interactions and pathways","date":"2013-11-14","arxiv_id":"1311.3355","repositories_listed":0,"syntology":null},{"url":null,"slug":"geospatial-narratives-and-their-spatio","title":"Geospatial Narratives and their Spatio-Temporal Dynamics: Commonsense Reasoning for High-level Analyses in Geographic Information Systems","date":"2013-07-09","arxiv_id":"1307.2541","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-fusion-by-matrix-factorization","title":"Data Fusion by Matrix Factorization","date":"2013-07-02","arxiv_id":"1307.0803","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-markov-model-for-ontology-alignment","title":"A Markov Model for Ontology Alignment","date":"2013-04-20","arxiv_id":"1304.5566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-learning-without-label","title":"Multitask Learning without Label Correspondences","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"74cb01fdbea53cfd6dac54567d06d14a5edcbeced80a7e17de717fbc3f1056ad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}