{"id":"https://openalex.org/W4387030229","doi":"https://doi.org/10.1109/e-science58273.2023.10254859","title":"A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks","display_name":"A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387030229","doi":"https://doi.org/10.1109/e-science58273.2023.10254859"},"language":"en","primary_location":{"id":"doi:10.1109/e-science58273.2023.10254859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/a-dense-retrieval-system-and-evaluation-dataset-for-scientific-computational-notebooks(5868e44f-6e5f-48fd-9f8a-a175a5dd6537).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100368028","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-7799-876X"},"institutions":[{"id":"https://openalex.org/I55106644","display_name":"Amsterdam University of Applied Sciences","ror":"https://ror.org/00y2z2s03","country_code":"NL","type":"education","lineage":["https://openalex.org/I55106644"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Na Li","raw_affiliation_strings":["Multiscale Networked System, Informatics Institute, University of Amsterdam,Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam,Netherlands","institution_ids":["https://openalex.org/I55106644"]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043638432","display_name":"Yangjun Zhang","orcid":"https://orcid.org/0009-0005-2663-5041"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yangjun Zhang","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London,United Kingdom","School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London,United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I55106644","display_name":"Amsterdam University of Applied Sciences","ror":"https://ror.org/00y2z2s03","country_code":"NL","type":"education","lineage":["https://openalex.org/I55106644"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhiming Zhao","raw_affiliation_strings":["Multiscale Networked System, Informatics Institute, University of Amsterdam,Netherlands","LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Amsterdam, Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam,Netherlands","institution_ids":["https://openalex.org/I55106644"]},{"raw_affiliation_string":"LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Amsterdam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100368028"],"corresponding_institution_ids":["https://openalex.org/I55106644","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.345,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66278682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259112238883972},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5604100823402405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5523656606674194},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5456268787384033},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5247552394866943},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.49991345405578613},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46700629591941833},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.45784538984298706},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.4551626443862915},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42174091935157776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22016653418540955},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14143788814544678},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1310189664363861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259112238883972},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5604100823402405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5523656606674194},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5456268787384033},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5247552394866943},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49991345405578613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46700629591941833},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.45784538984298706},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.4551626443862915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42174091935157776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22016653418540955},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14143788814544678},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1310189664363861},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/e-science58273.2023.10254859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/5868e44f-6e5f-48fd-9f8a-a175a5dd6537","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/a-dense-retrieval-system-and-evaluation-dataset-for-scientific-computational-notebooks(5868e44f-6e5f-48fd-9f8a-a175a5dd6537).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, N, Zhang, Y & Zhao, Z 2023, A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks. in 2023 IEEE 19th International Conference on e-Science : (e-Science) : October 9-14, 2023, Limassol, Cyprus : proceedings., 19, Piscataway, NJ, pp. 179-188, 19th IEEE International Conference on e-Science, e-Science 2023, Limassol, Cyprus, 9/10/23. https://doi.org/10.1109/e-Science58273.2023.10254859","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:zenodo.org:8413983","is_oa":true,"landing_page_url":"https://zenodo.org/record/8413983","pdf_url":"https://zenodo.org/record/8413983","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/5868e44f-6e5f-48fd-9f8a-a175a5dd6537","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/a-dense-retrieval-system-and-evaluation-dataset-for-scientific-computational-notebooks(5868e44f-6e5f-48fd-9f8a-a175a5dd6537).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, N, Zhang, Y & Zhao, Z 2023, A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks. in 2023 IEEE 19th International Conference on e-Science : (e-Science) : October 9-14, 2023, Limassol, Cyprus : proceedings., 19, Piscataway, NJ, pp. 179-188, 19th IEEE International Conference on e-Science, e-Science 2023, Limassol, Cyprus, 9/10/23. https://doi.org/10.1109/e-Science58273.2023.10254859","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1974542962","display_name":null,"funder_award_id":"Sk\u0142odowska","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2300613588","display_name":null,"funder_award_id":"860627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3912856170","display_name":null,"funder_award_id":"824068","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7761236267","display_name":null,"funder_award_id":"862409","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7835511776","display_name":"AP4L: Adaptive PETs to Protect &amp; emPower People during Life Transitions","funder_award_id":"EP/W032473/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8452545418","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8764417039","display_name":"smART socIal media eCOsytstem in a blockchaiN Federated environment","funder_award_id":"825134","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320325020","display_name":"LifeWatch \u2013 Niclas \u00d6berg Foundation","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2247374552","https://openalex.org/W2254368993","https://openalex.org/W2784241156","https://openalex.org/W2794601162","https://openalex.org/W2805788202","https://openalex.org/W2896457183","https://openalex.org/W2898671507","https://openalex.org/W2951534261","https://openalex.org/W2968179027","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3008721012","https://openalex.org/W3016473712","https://openalex.org/W3094700537","https://openalex.org/W3098605233","https://openalex.org/W3099700870","https://openalex.org/W3119507053","https://openalex.org/W3127102982","https://openalex.org/W3137305332","https://openalex.org/W3145630588","https://openalex.org/W3162449204","https://openalex.org/W3198431451","https://openalex.org/W3214554611","https://openalex.org/W3215151014","https://openalex.org/W4226018502","https://openalex.org/W4226325130","https://openalex.org/W4287647122","https://openalex.org/W4367309763","https://openalex.org/W4389921502","https://openalex.org/W6628905179","https://openalex.org/W6755207826","https://openalex.org/W6764357534","https://openalex.org/W6774181064","https://openalex.org/W6776148200","https://openalex.org/W6783227185","https://openalex.org/W6783675033","https://openalex.org/W6804229246","https://openalex.org/W6846956741","https://openalex.org/W6948361469"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W1511521437","https://openalex.org/W2950904665","https://openalex.org/W4289376745","https://openalex.org/W1597205557","https://openalex.org/W1731132221","https://openalex.org/W4214707141","https://openalex.org/W2058799936","https://openalex.org/W2378302565","https://openalex.org/W17854358"],"abstract_inverted_index":{"The":[0,172],"discovery":[1],"and":[2,24,49,147,152,170,192],"reutilization":[3],"of":[4,64,116,168],"scientific":[5,26,143],"codes":[6],"are":[7],"crucial":[8],"in":[9,54,118,166],"many":[10],"research":[11,79],"activities.":[12],"Computational":[13],"notebooks":[14,33,40,133],"have":[15,83],"emerged":[16],"as":[17,89,178],"a":[18,35,90,125,179],"particularly":[19],"effective":[20],"medium":[21],"for":[22,58,67,100,150],"sharing":[23],"reusing":[25],"codes.":[27],"Nevertheless,":[28],"effectively":[29],"locating":[30],"relevant":[31],"computational":[32,39,69,86,102,120,132,145],"is":[34],"significant":[36],"challenge.":[37],"First,":[38],"encompass":[41],"multi-modal":[42],"data":[43,57],"comprising":[44],"unstructured":[45],"text,":[46],"source":[47],"code,":[48],"other":[50,190],"media,":[51],"posing":[52],"complexities":[53],"representing":[55],"such":[56],"retrieval":[59,128],"purposes.":[60],"Second,":[61],"the":[62,68,78,106,113,160],"absence":[63],"evaluation":[65,139],"datasets":[66],"notebook":[70,87],"search":[71,88,92],"task":[72],"hampers":[73],"fair":[74,151],"performance":[75,154],"assessments":[76],"within":[77],"community.":[80],"Prior":[81],"studies":[82],"either":[84],"treated":[85],"code-snippet":[91],"problem":[93],"or":[94],"focused":[95],"solely":[96],"on":[97],"content-based":[98],"approaches":[99,165],"searching":[101],"notebooks.":[103,121],"To":[104],"address":[105],"aforementioned":[107],"difficulties,":[108],"we":[109,136],"present":[110],"DeCNR,":[111],"tackling":[112],"information":[114],"needs":[115],"researchers":[117],"seeking":[119],"Our":[122],"approach":[123],"leverages":[124],"fused":[126],"sparse-dense":[127],"model":[129],"to":[130],"represent":[131],"effectively.":[134],"Additionally,":[135],"construct":[137],"an":[138],"dataset":[140],"including":[141],"actual":[142],"queries,":[144],"notebooks,":[146],"relevance":[148],"judgments":[149],"objective":[153],"assessment.":[155],"Experimental":[156],"results":[157],"demonstrate":[158],"that":[159],"proposed":[161,173],"method":[162],"surpasses":[163],"baseline":[164],"terms":[167],"F1@5":[169],"NDCG@5.":[171],"system":[174],"has":[175],"been":[176],"implemented":[177],"web":[180,193],"service":[181],"shipped":[182],"with":[183,189],"REST":[184],"APIs,":[185],"allowing":[186],"seamless":[187],"integration":[188],"applications":[191],"services.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
