1"""Area data_distributed, part A: categories 20-22 (databases, information retrieval, distributed computing)."""23CATEGORIES = [4dict(5 id="database_systems", number=20, name="Database Systems", area="data_distributed",6 definition=("Storage, querying and management of structured and semi-structured data: query processing and optimisation, "7 "transactions and concurrency control, indexing and storage engines, data integration, cleaning and provenance, "8 "big-data processing frameworks, data mining as a data-management problem, learned database components, "9 "vector and graph databases. Ranking of unstructured documents is information_retrieval."),10 topics=[("T10317", 1.0, "advanced database systems and queries"), ("T12761", 0.6, "data stream mining"),11 ("T11719", 0.6, "data quality and management"), ("T14280", 0.6, "big data technologies and applications"),12 ("T10538", 0.5, "data mining algorithms and applications"), ("T11181", 0.5, "advanced data storage technologies"),13 ("T12601", 0.5, "web applications and data management"), ("T11106", 0.5, "data management and algorithms"),14 ("T10772", 0.4, "distributed systems and fault tolerance (distributed databases, transactions)"),15 ("T13373", 0.4, "data mining and ML applications"), ("T11891", 0.4, "big data and business intelligence"),16 ("T10215", 0.4, "semantic web and ontologies (RDF, SPARQL)"), ("T12016", 0.4, "web data mining"),17 ("T14435", 0.4, "information retrieval and data mining"), ("T11937", 0.3, "research data management"),18 ("T13647", 0.3, "AI and big data applications"), ("T14347", 0.2, "big data and digital economy"),19 ("T10101", 0.2, "cloud computing (MapReduce, Hadoop)"), ("T10757", 0.2, "geographic information systems"),20 ("T13832", 0.2, "advanced decision-making techniques (DSS)"), ("T14484", 0.2, "technology and data analysis")],21 subfields=[(1710, 0.1)],22 arxiv=[("cs.DB", 1.0)],23 streams=[("conf/sigmod", 1.0), ("journals/pvldb", 1.0), ("journals/pacmmod", 1.0), ("conf/icde", 1.0), ("conf/edbt", 1.0),24 ("conf/pods", 1.0), ("journals/tods", 1.0), ("journals/vldb", 1.0), ("conf/dasfaa", 1.0), ("conf/vldb", 0.8),25 ("journals/tkde", 0.8), ("journals/tbd", 0.6), ("conf/apweb", 0.6), ("conf/icdm", 0.5), ("conf/pakdd", 0.5),26 ("journals/tkdd", 0.5), ("journals/kais", 0.5), ("conf/bigdataconf", 0.5), ("journals/jbd", 0.5), ("conf/gis", 0.5),27 ("conf/cikm", 0.4), ("conf/kdd", 0.4), ("journals/ijdsa", 0.4), ("journals/data", 0.4), ("conf/pkdd", 0.3),28 ("journals/www", 0.3), ("journals/tgis", 0.3), ("journals/gis", 0.3), ("journals/biodb", 0.3),29 ("conf/semweb", 0.3), ("conf/esws", 0.3), ("journals/dss", 0.2), ("journals/isf", 0.1), ("journals/tist", 0.2),30 ("journals/kbs", 0.1), ("conf/ksem", 0.2)],31 keywords=[32 (r"(?i)\bdatabases?\b|\bDBMSs?\b|\bRDBMSs?\b|\bdatabase (systems?|management|engines?|design|theory|queries|tuning|research)\b", 0.8, "both"),33 (r"(?i)\b(query (processing|optimi[sz]ation|execution|languages?|engines?|compilation|plans?|rewriting|answering over)|SQL\b|NoSQL|NewSQL|relational (model|algebra|databases?|queries|tables?)|transaction(al)? (processing|management|systems?)|ACID\b|OLTP|OLAP|HTAP|index(ing|es) (structures?|for|techniques)|B\+?-?trees?|learned (index(es)?|cardinality|query optimi[sz]ers?|database)|key-?value stores?|column(ar)? (stores?|storage|formats?)|data (warehous(e|es|ing)|lakes?|lakehouses?|integration|cleaning|quality|provenance|lineage|wrangling|catalogs?|cubes?|partitioning|versioning|discovery|marketplaces?)|schema (matching|evolution|mapping|inference)|entity (resolution|matching)|record linkage|join (algorithms?|processing|ordering|optimi[sz]ation)|cardinality estimation|selectivity estimation|data management|graph databases?|property graphs?|spatial (databases?|indexing|queries|joins?)|spatio-?temporal (databases?|queries|indexing)|time[- ]series databases?|vector (databases?|search engines?|indexes?)|approximate nearest neighbou?r search|similarity search|top-?k queries|skyline queries|query by example|data lakes?|metadata management|Datalog engines?)\b", 1.0, "both"),34 (r"(?i)\b(data mining|frequent (patterns?|itemsets?|subgraphs?)|association rules?|knowledge discovery in databases|KDD\b|sequential pattern mining|stream (processing|mining)|data streams?|sliding windows?|big data (analytics|processing|systems?|platforms?|frameworks?|management)|Hadoop|HDFS|Apache Spark|Spark SQL|MapReduce|Flink|Hive|Presto|Trino|Kafka|ETL\b|ELT\b|text-?to-?SQL|NL2SQL|natural language interfaces? to databases?|NLIDB|LLMs? for (data|databases?|SQL|tables?)|table (question answering|understanding|representation))\b", 0.7, "both"),35 (r"(?i)\b(PostgreSQL|Postgres|MySQL|SQLite|DuckDB|MongoDB|Cassandra|RocksDB|LevelDB|Neo4j|ClickHouse|Snowflake|BigQuery|Redshift|TiDB|CockroachDB|Spanner|DynamoDB|LSM-?trees?|storage engines?|buffer (pool|management)|concurrency control|MVCC|multi-?version|crash recovery|write-?ahead log(ging)?|WAL\b|checkpointing in databases|isolation levels?|serializab(le|ility)|snapshot isolation|two-?phase (locking|commit)|optimistic concurrency|deterministic databases?|in-?memory databases?|main-?memory databases?|disaggregated (storage|memory) for databases?|cloud(-?native)? databases?|database-?as-?a-?service|DBaaS|multi-?model databases?|time-?travel queries|temporal databases?)\b", 1.0, "both"),36 (r"(?i)\b(data|queries|query|tables?|records?|tuples?|schemas?|indexes|indices)\b", 0.2, "both"),37 ],38 exclusions=[r"(?is)^(?!.*(query processing|SQL|transaction|index(ing)?|storage engine|DBMS|data management|data integration|schema|NoSQL|query optimi)).*\b(PubMed|Embase|Scopus|Web of Science|Cochrane|MEDLINE|CINAHL|PsycINFO) (databases?|were searched|search)\b"],39 related=["information_retrieval", "distributed_computing", "cloud_computing", "algorithms", "ml_theory"],40 parent_of=[], child_of=[],41 provenance=("T10317 is the OpenAlex database topic; data-mining and big-data topics (1710, 1711, 18xx) shared at 0.4-0.6. "42 "SIGMOD/PVLDB/PACMMOD/ICDE/EDBT/PODS/TODS/VLDBJ pure; CIKM/KDD shared with IR and ML. Systematic-review "43 "mentions of bibliographic databases are vetoed when no DB-systems term co-occurs."),44),45dict(46 id="information_retrieval", number=21, name="Information Retrieval", area="data_distributed",47 definition=("Finding and ranking relevant information for a user need: search engines and ranking models, dense and "48 "sparse retrieval, recommender systems, query understanding, evaluation and test collections, web search and "49 "mining, scholarly and digital-library retrieval, retrieval components of RAG systems. Structured query "50 "processing is database_systems; text understanding tasks are nlp."),51 topics=[("T10286", 1.0, "information retrieval and search behavior"), ("T10203", 1.0, "recommender systems"),52 ("T13274", 0.8, "expert finding and Q&A systems"), ("T14435", 0.6, "information retrieval and data mining"),53 ("T13976", 0.5, "web visibility and informetrics"), ("T12016", 0.5, "web data mining and analysis"),54 ("T10627", 0.4, "advanced image and video retrieval"), ("T10824", 0.3, "image retrieval and classification"),55 ("T10028", 0.3, "topic modeling / RAG / sentence retrieval"), ("T10215", 0.3, "semantic web and ontologies"),56 ("T13673", 0.2, "library science and information"), ("T11937", 0.2, "research data management"),57 ("T11813", 0.2, "library collection development and digital resources"), ("T12863", 0.2, "web and library services"),58 ("T10664", 0.2, "sentiment analysis and opinion mining"), ("T11644", 0.2, "spam and phishing detection"),59 ("T14330", 0.2, "library science and information systems"), ("T13166", 0.2, "information science and libraries"),60 ("T13874", 0.2, "information architecture and usability"), ("T11122", 0.2, "online learning and analytics (recommendation)")],61 subfields=[(1710, 0.1)],62 arxiv=[("cs.IR", 1.0), ("cs.DL", 0.6), ("cs.SI", 0.3)],63 streams=[("conf/sigir", 1.0), ("conf/wsdm", 1.0), ("conf/ecir", 1.0), ("conf/recsys", 1.0), ("journals/tois", 1.0),64 ("journals/ipm", 0.8), ("conf/clef", 0.8), ("conf/jcdl", 0.8), ("conf/um", 0.8), ("conf/cikm", 0.6), ("conf/www", 0.6),65 ("journals/www", 0.6), ("journals/jasis", 0.6), ("conf/asist", 0.6), ("journals/scientometrics", 0.5),66 ("conf/semweb", 0.5), ("conf/esws", 0.5), ("conf/webi", 0.5), ("journals/kais", 0.3), ("conf/kdd", 0.3),67 ("conf/icwsm", 0.3), ("journals/tist", 0.3), ("journals/tkde", 0.2), ("journals/snam", 0.2), ("conf/asunam", 0.2),68 ("journals/tcss", 0.1), ("journals/ijinfoman", 0.2), ("journals/jkm", 0.1), ("journals/iam", 0.1)],69 keywords=[70 (r"(?i)\binformation retrieval\b|\bIR (systems?|models?|evaluation|research|community)\b|\bad[- ]hoc retrieval\b|\bretrieval (models?|systems?|effectiveness|augmented)\b", 1.0, "both"),71 (r"(?i)\b(search engines?|web search|enterprise search|product search|query (expansion|reformulation|understanding|suggestion|logs?|auto-?completion|intent)|ranking (models?|functions?|losses?|metrics)|learning[- ]to[- ]rank|LTR\b|dense (retrieval|passage retrieval|retrievers?)|sparse retrieval|lexical retrieval|hybrid retrieval|BM25|TF-?IDF|neural (retrieval|rankers?|IR|re-?ranking)|re-?rank(ing|ers?)|cross-?encoders?|bi-?encoders?|dual encoders?|ColBERT|late interaction|SPLADE|DPR\b|document (ranking|retrieval|expansion)|passage (ranking|retrieval)|relevance (judgments?|feedback|assessment|modeling)|click (models?|logs?|through)|conversational search|interactive (IR|retrieval)|session search|evaluation (campaigns?|measures?)|nDCG|MRR\b|mean reciprocal rank|MAP@|test collections?|TREC\b|MS ?MARCO|BEIR|pooling bias|query performance prediction|retrieval-?augmented|RAG (systems?|pipelines?)|retriever|generative (retrieval|recommendation))\b", 1.0, "both"),72 (r"(?i)\brecommend(er|ation) (systems?|models?|algorithms?|engines?|tasks?|lists?|quality)\b|\brecommenders?\b|\bcollaborative filtering\b|\b(sequential|session-?based|conversational|cross-?domain|cold-?start|news|music|point-?of-?interest|POI|job|group|bundle|LLM-?based|explainable|fair|multi-?stakeholder) recommendation\b|\bclick-?through rate\b|\bCTR prediction\b|\bimplicit feedback\b|\buser (modeling|preferences?|interests?) (for|in) recommendation\b|\bmatrix factori[sz]ation\b|\bitem (embeddings?|cold start)\b|\bMovieLens\b|\bNetflix Prize\b", 1.0, "both"),73 (r"(?i)\b(knowledge graphs?|entity linking|entity search|semantic web|linked (open )?data|SPARQL|RDF\b|ontolog(y|ies) (matching|alignment|engineering)|schema\.org|Wikidata|DBpedia|question answering over knowledge)\b", 0.5, "both"),74 (r"(?i)\b(digital librar(y|ies)|scholarly (search|recommendation|data|documents?|knowledge graphs?)|citation (analysis|networks?|recommendation|counts?|indexing)|bibliometric|scientometric|altmetric|h-?index|peer[- ]review (process|quality)|web (crawl(ing|ers?)|archiv(es?|ing)|mining)|social media (mining|analytics|retrieval)|hashtags?|microblog|user-?generated content|community question answering|CQA\b|expert finding|e-?commerce search|sponsored search|computational advertising|ad (auctions?|ranking))\b", 0.6, "both"),75 (r"(?i)\b(retrieval|search|ranking|recommendation|relevance|queries|query|users?' (information|search))\b", 0.3, "both"),76 ],77 exclusions=[],78 related=["nlp", "database_systems", "llm", "hci", "ml_theory"],79 parent_of=[], child_of=[],80 provenance=("T10286 (search behaviour) and T10203 (recommenders) are the OpenAlex IR hosts; library/information-science "81 "topics of 1710 included at 0.2 because they share venues (JASIST, ASIS&T). SIGIR/WSDM/ECIR/RecSys/TOIS pure."),82),83dict(84 id="distributed_computing", number=22, name="Distributed Computing", area="data_distributed",85 definition=("Computation across multiple processors or machines: distributed algorithms and consensus, fault tolerance "86 "and replication, parallel programming and HPC systems software, cluster and grid resource management, "87 "distributed storage and middleware, distributed and parallel ML training systems. Cloud service models are "88 "cloud_computing and edge placement is edge_computing (both children)."),89 topics=[("T10715", 1.0, "distributed and parallel computing systems (grid, cluster, scheduling)"),90 ("T10772", 1.0, "distributed systems and fault tolerance (consensus, replication, transactions)"),91 ("T10742", 0.8, "peer-to-peer network technologies"), ("T10054", 0.6, "parallel computing (HPC, MPI, GPU)"),92 ("T10829", 0.5, "interconnection networks and systems"), ("T11181", 0.5, "advanced data storage technologies"),93 ("T10101", 0.4, "cloud computing and resource management"), ("T12127", 0.4, "software system performance and reliability"),94 ("T10679", 0.3, "service-oriented architecture"), ("T10273", 0.3, "IoT and edge/fog computing"),95 ("T10249", 0.3, "distributed control multi-agent systems"), ("T12203", 0.3, "mobile agent-based network management"),96 ("T11986", 0.3, "scientific workflows"), ("T12879", 0.2, "distributed sensor networks and detection"),97 ("T12216", 0.2, "network time synchronization"), ("T11478", 0.2, "caching and content delivery")],98 subfields=[(1705, 0.1)],99 arxiv=[("cs.DC", 1.0), ("cs.PF", 0.5), ("cs.OS", 0.2), ("cs.NI", 0.1)],100 streams=[("journals/tpds", 1.0), ("journals/jpdc", 1.0), ("conf/ipps", 1.0), ("conf/podc", 1.0), ("conf/spaa", 1.0),101 ("conf/opodis", 1.0), ("conf/europar", 1.0), ("conf/ics", 1.0), ("conf/hpdc", 1.0), ("conf/icdcs", 1.0),102 ("conf/middleware", 1.0), ("conf/cluster", 1.0), ("conf/icpads", 1.0), ("conf/ica3pp", 1.0), ("conf/ispa", 1.0),103 ("conf/sc", 0.8), ("conf/ccgrid", 0.8), ("conf/hpcc", 0.8), ("conf/ppopp", 0.8), ("journals/concurrency", 0.8),104 ("journals/tjs", 0.8), ("journals/cluster", 0.8), ("journals/ijhpca", 0.8), ("journals/scpe", 0.8),105 ("journals/fgcs", 0.6), ("conf/eurosys", 0.6), ("journals/ppna", 0.6), ("conf/aina", 0.6), ("conf/nsdi", 0.5),106 ("conf/dsn", 0.5), ("conf/socc", 0.5), ("conf/cloud", 0.5), ("journals/tos", 0.5), ("conf/fast", 0.5),107 ("conf/osdi", 0.4), ("conf/sosp", 0.4), ("journals/tc", 0.4), ("journals/sp", 0.4), ("conf/mlsys", 0.4),108 ("conf/ucc", 0.4), ("journals/tcc", 0.3), ("journals/jsa", 0.3), ("journals/computing", 0.3),109 ("journals/tnsm", 0.2), ("conf/xsede", 0.4), ("conf/pact", 0.2), ("journals/taco", 0.1), ("journals/tnse", 0.2),110 ("journals/jnca", 0.2), ("conf/isca", 0.1), ("journals/ieicetd", 0.1)],111 keywords=[112 (r"(?i)\b(distributed|parallel|concurrent) (systems?|computing|algorithms?|programming|processing|storage|file systems?|transactions?|consensus|ledgers?|training|inference|machine learning|deep learning|graph processing|databases?|data processing|simulation|applications?|execution|runtime|scheduling|snapshots?|shared memory|memory|protocols?|optimi[sz]ation|SGD|stochastic)\b", 1.0, "both"),113 (r"(?i)\b(consensus (protocols?|algorithms?)|Paxos|Raft\b|Byzantine|fault[- ]toleran(t|ce)|replication|state machine replication|linearizab(le|ility)|serializab|eventual consistency|strong consistency|consistency models?|CRDTs?|conflict-?free replicated|vector clocks?|logical clocks?|leader election|gossip protocols?|epidemic protocols?|distributed (hash tables?|locks?|snapshots?|tracing|ledger|shared)|two-?phase commit|atomic (broadcast|commit)|failure detectors?|self-?stabili[sz]|population protocols?|LOCAL model|CONGEST|message complexity|round complexity|asynchronous (systems?|networks?|model))\b", 1.0, "both"),114 (r"(?i)\b(high[- ]performance computing|HPC\b|supercomput\w+|exascale|petascale|MPI\b|OpenMP|message passing|load balancing|job scheduling|workflow (scheduling|management|engines?)|resource (allocation|management|scheduling) (in|for|on|across) (clusters?|grids?|data ?cent(er|re)s?|HPC|supercomputers?)|scalab(le|ility) (to|on|across) \d[\d,]* (nodes|cores|GPUs|processors)|multi-?GPU|GPU clusters?|data[- ]parallel(ism)?|model[- ]parallel(ism)?|pipeline[- ]parallel(ism)?|tensor[- ]parallel(ism)?|expert parallelism|all-?reduce|all-?to-?all|parameter servers?|collective communication|NCCL|ZeRO\b|FSDP|DeepSpeed|Megatron|Horovod|gradient (synchroni[sz]ation|accumulation across)|stragglers?|checkpoint(ing)? (for|of|in) (training|HPC)|large-?scale training|training (at scale|on \d+ GPUs)|distributed (LLM|DNN) (training|inference|serving)|cluster schedul(ers?|ing)|Slurm|Kubernetes schedul|Borg|YARN|Mesos)\b", 1.0, "both"),115 (r"(?i)\b(middleware|publish[- ]subscribe|pub/sub|message (queues?|brokers?)|Kafka|RabbitMQ|actor model|service mesh|stream processing (engines?|systems?|frameworks?)|Apache (Spark|Flink|Storm|Beam|Hadoop)|MapReduce|Ray\b|Dask|dataflow (systems?|engines?)|serverless (workflows?|computing)|microservices? (architecture|performance|systems?)|RPC\b|remote procedure|gRPC|RDMA|interconnects?|InfiniBand|network-?on-?chip)\b", 0.7, "both"),116 (r"(?i)\b(peer-?to-?peer|P2P\b|overlay networks?|volunteer computing|grid computing|cluster computing|utility computing|desktop grid|BOINC|BitTorrent|DHTs?\b|Chord|Kademlia|gossip-?based)\b", 0.8, "both"),117 (r"(?i)\b(multi-?core|many-?core|multi-?threaded|multithreading|lock-?free|wait-?free|non-?blocking (data structures?|algorithms?)|transactional memory|synchroni[sz]ation primitives|mutex(es)?|spin-?locks?|barriers?|work[- ]stealing|parallel(i[sz]ation|ism|izing)|task (parallel|graphs?)|speedup|Amdahl|strong scaling|weak scaling|parallel efficiency|SIMD parallel|GPU (computing|programming|acceleration)|CUDA\b|OpenCL|heterogeneous computing)\b", 0.8, "both"),118 (r"(?i)\b(nodes?|clusters?|scalab(le|ility)|parallel|distributed|concurrency|replicas?|throughput|latency)\b", 0.2, "both"),119 ],120 exclusions=[r"(?is)^(?!.*(comput|system|algorithm|protocol|network|server|cluster|node|GPU|processor|storage|training|software)).*\b(distributed (generation|energy resources?|lag|fibre|fiber|acoustic|temperature|parameter|load|element|order|delay|control of (power|microgrid|vehicles?|robots?)|leadership|cognition|practice|manufacturing))\b"],121 related=["cloud_computing", "edge_computing", "computer_networks", "database_systems", "operating_systems", "scientific_computing", "blockchain", "federated_learning"],122 parent_of=["cloud_computing", "edge_computing"], child_of=[],123 provenance=("T10715 and T10772 (subfield 1705) are the OpenAlex hosts; T10054 (parallel/HPC) is shared with architecture and "124 "scientific computing. TPDS/JPDC/IPDPS/PODC/SPAA/Euro-Par/ICS/HPDC/ICDCS/Middleware are the pure venues; cs.DC suffices."),125),126]127