{"id":"https://openalex.org/W4412377927","doi":"https://doi.org/10.1145/3726302.3730342","title":"REANIMATOR: Reanimate Retrieval Test Collections with Extracted and Synthetic Resources","display_name":"REANIMATOR: Reanimate Retrieval Test Collections with Extracted and Synthetic Resources","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377927","doi":"https://doi.org/10.1145/3726302.3730342"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730342","doi":"https://doi.org/10.1145/3726302.3730342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730342","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730342","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009996015","display_name":"Bj\u00f6rn Engelmann","orcid":"https://orcid.org/0009-0000-7074-9066","observed_orcids":["https://orcid.org/0009-0000-7074-9066"]},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Engelmann","raw_affiliation_strings":["TH K\u00f6ln, Cologne, Germany"],"raw_orcid":"https://orcid.org/0009-0000-7074-9066","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln, Cologne, Germany","institution_ids":["https://openalex.org/I102520234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085724158","display_name":"Fabian Haak","orcid":"https://orcid.org/0000-0002-3392-7860","observed_orcids":["https://orcid.org/0000-0002-3392-7860"]},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Haak","raw_affiliation_strings":["TH K\u00f6ln, Cologne, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3392-7860","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln, Cologne, Germany","institution_ids":["https://openalex.org/I102520234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087564658","display_name":"Philipp Schaer","orcid":"https://orcid.org/0000-0002-8817-4632","observed_orcids":["https://orcid.org/0000-0002-8817-4632"]},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Schaer","raw_affiliation_strings":["TH K\u00f6ln, Cologne, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8817-4632","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln, Cologne, Germany","institution_ids":["https://openalex.org/I102520234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026436360","display_name":"Mani Erfanian Abdoust","orcid":"https://orcid.org/0009-0008-8791-6455","observed_orcids":["https://orcid.org/0009-0008-8791-6455"]},"institutions":[{"id":"https://openalex.org/I4387154585","display_name":"Science Media Center Germany","ror":"https://ror.org/03fc7m932","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4387154585"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mani Erfanian Abdoust","raw_affiliation_strings":["Science Media Center, Cologne, Germany"],"raw_orcid":"https://orcid.org/0009-0008-8791-6455","affiliations":[{"raw_affiliation_string":"Science Media Center, Cologne, Germany","institution_ids":["https://openalex.org/I4387154585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118969384","display_name":"Linus Netze","orcid":"https://orcid.org/0009-0000-4392-9897","observed_orcids":["https://orcid.org/0009-0000-4392-9897"]},"institutions":[{"id":"https://openalex.org/I4387154585","display_name":"Science Media Center Germany","ror":"https://ror.org/03fc7m932","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4387154585"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Linus Netze","raw_affiliation_strings":["Science Media Center, Cologne, Germany"],"raw_orcid":"https://orcid.org/0009-0000-4392-9897","affiliations":[{"raw_affiliation_string":"Science Media Center, Cologne, Germany","institution_ids":["https://openalex.org/I4387154585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006485784","display_name":"Meik Bittkowski","orcid":"https://orcid.org/0009-0005-4668-6030","observed_orcids":["https://orcid.org/0009-0005-4668-6030"]},"institutions":[{"id":"https://openalex.org/I4387154585","display_name":"Science Media Center Germany","ror":"https://ror.org/03fc7m932","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4387154585"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meik Bittkowski","raw_affiliation_strings":["Science Media Center, Cologne, Germany"],"raw_orcid":"https://orcid.org/0009-0005-4668-6030","affiliations":[{"raw_affiliation_string":"Science Media Center, Cologne, Germany","institution_ids":["https://openalex.org/I4387154585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1772,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77810822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3691","last_page":"3701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.0007999999797903001,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9599999785423279},{"id":"https://openalex.org/keywords/table-extraction","display_name":"table extraction","score":0.6150000095367432},{"id":"https://openalex.org/keywords/pdf-parsing","display_name":"PDF parsing","score":0.5220000147819519},{"id":"https://openalex.org/keywords/human-in-the-loop-validation","display_name":"human-in-the-loop validation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/information-retrieval-evaluation","display_name":"information retrieval evaluation","score":0.6129999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662179231643677},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6282292008399963},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4023776650428772},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730342","doi":"https://doi.org/10.1145/3726302.3730342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730342","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730342","doi":"https://doi.org/10.1145/3726302.3730342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730342","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3273974344","display_name":null,"funder_award_id":"00.003.2020","funder_id":"https://openalex.org/F4320324316","funder_display_name":"Klaus Tschira Stiftung"},{"id":"https://openalex.org/G5879751697","display_name":"PIXLS  Preprint Information eXtraction for Life Sciences","funder_award_id":"492813820","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6253893277","display_name":null,"funder_award_id":"492813820","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6465787304","display_name":null,"funder_award_id":"00.003.2020","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320324316","display_name":"Klaus Tschira Stiftung","ror":"https://ror.org/052jep661"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377927.pdf","grobid_xml":"https://content.openalex.org/works/W4412377927.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1977437814","https://openalex.org/W2022995284","https://openalex.org/W2026032877","https://openalex.org/W2048747249","https://openalex.org/W2145790509","https://openalex.org/W2148972377","https://openalex.org/W2698462918","https://openalex.org/W2796806625","https://openalex.org/W2809941908","https://openalex.org/W3034471540","https://openalex.org/W3034944976","https://openalex.org/W3128581554","https://openalex.org/W3133594109","https://openalex.org/W3138967041","https://openalex.org/W3156166379","https://openalex.org/W4284699573","https://openalex.org/W4294501307","https://openalex.org/W4387800835","https://openalex.org/W4389984066","https://openalex.org/W4392870000","https://openalex.org/W4399605340","https://openalex.org/W4400341981","https://openalex.org/W4400342194","https://openalex.org/W4400526284","https://openalex.org/W4400526908","https://openalex.org/W4400528879","https://openalex.org/W4402670290","https://openalex.org/W4404780697","https://openalex.org/W7093349750"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Retrieval":[0],"test":[1,34,46,103,127],"collections":[2,35,47,128],"are":[3],"essential":[4],"for":[5,129],"evaluating":[6,114],"information":[7],"retrieval":[8],"systems,":[9],"yet":[10],"they":[11],"often":[12],"lack":[13],"generalizability":[14],"across":[15],"tasks.":[16],"To":[17],"overcome":[18],"this":[19],"limitation,":[20],"we":[21],"introduce":[22],"REANIMATOR,":[23],"a":[24,97,109],"versatile":[25],"framework":[26],"designed":[27],"to":[28,71],"enable":[29],"the":[30,84,101,106,115,124,136],"repurposing":[31],"of":[32,100,108,117,126,138],"existing":[33],"by":[36,51],"enriching":[37],"them":[38],"with":[39,96],"extracted":[40,89],"and":[41,55,90,113,134],"synthetic":[42,73],"resources.":[43,140],"REANIMATOR":[44,122],"enhances":[45],"from":[48],"PDF":[49],"files":[50],"parsing":[52],"full":[53],"texts":[54],"machine-readable":[56],"tables,":[57],"as":[58,60],"well":[59],"related":[61],"contextual":[62],"information.":[63],"It":[64],"then":[65],"employs":[66],"state-of-the-art":[67],"large":[68],"language":[69],"models":[70],"produce":[72],"relevance":[74],"labels.":[75],"Including":[76],"an":[77],"optional":[78],"human-in-the-loop":[79],"step":[80],"can":[81],"help":[82],"validate":[83],"resources":[85],"that":[86],"have":[87],"been":[88],"generated.":[91],"We":[92],"demonstrate":[93],"its":[94],"potential":[95],"revitalized":[98],"version":[99],"TREC-COVID":[102],"collection,":[104],"showcasing":[105],"development":[107],"retrieval-augmented":[110,120],"generation":[111],"system":[112],"impact":[116],"tables":[118],"on":[119],"generation.":[121],"enables":[123],"reuse":[125],"new":[130],"applications,":[131],"lowering":[132],"costs":[133],"broadening":[135],"utility":[137],"legacy":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}