{"id":"https://openalex.org/W7220693231","doi":"https://doi.org/10.48550/arxiv.2610.06650","title":"Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents","display_name":"Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220693231","doi":"https://doi.org/10.48550/arxiv.2610.06650"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.06650","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06650","pdf_url":"https://arxiv.org/pdf/2610.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.06650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030631213","display_name":"Mohamed Chenene","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenene, Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119719389","display_name":"Carlos Rosas Hinostroza","orcid":"https://orcid.org/0009-0006-3507-0756","observed_orcids":["https://orcid.org/0009-0006-3507-0756"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I182627622","display_name":"Universit\u00e9 Sorbonne Nouvelle","ror":"https://ror.org/03z6jp965","country_code":"FR","type":"education","lineage":["https://openalex.org/I182627622"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rosas-Hinostroza, Carlos","raw_affiliation_strings":["Lattice , ENS-PSL , CNRS , Sorbonne Nouvelle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lattice , ENS-PSL , CNRS , Sorbonne Nouvelle","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I182627622","https://openalex.org/I2746051580","https://openalex.org/I29607241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149994612","display_name":"Anastasia Stasenko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stasenko, Anastasia","raw_affiliation_strings":["Universit\u00e9 Paris Dauphine-PSL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Dauphine-PSL","institution_ids":["https://openalex.org/I56435720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010378053","display_name":"Shani Evenstein Sigalov","orcid":"https://orcid.org/0000-0001-8823-540X","observed_orcids":["https://orcid.org/0000-0001-8823-540X"]},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I2802488147","display_name":"School of Advanced Study","ror":"https://ror.org/039594g80","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I2802488147"]},{"id":"https://openalex.org/I4405258462","display_name":"Digital Humanities Research Hub","ror":"https://ror.org/00pr69w48","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I2802488147","https://openalex.org/I4405258462"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sigalov, Shani Evenstein","raw_affiliation_strings":["AI-BRIDGES","Digital Humanities Research Hub , School of Advanced Study , University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI-BRIDGES","institution_ids":[]},{"raw_affiliation_string":"Digital Humanities Research Hub , School of Advanced Study , University of London","institution_ids":["https://openalex.org/I124357947","https://openalex.org/I2802488147","https://openalex.org/I4405258462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090355875","display_name":"Pierre-Carl Langlais","orcid":"https://orcid.org/0000-0001-9035-1127","observed_orcids":["https://orcid.org/0000-0001-9035-1127"]},"institutions":[{"id":"https://openalex.org/I4405256168","display_name":"m\u00e9dialab Sciences Po","ror":"https://ror.org/03vk15693","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205092303","https://openalex.org/I4405256168"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Langlais, Pierre-Carl","raw_affiliation_strings":["Sciences Po M\u00e9dialab","Sorbonne Center for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sciences Po M\u00e9dialab","institution_ids":["https://openalex.org/I4405256168"]},{"raw_affiliation_string":"Sorbonne Center for Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9140999913215637,"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":0.9140999913215637,"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":0.028200000524520874,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0203000009059906,"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/wikidata","display_name":"Wikidata","score":0.8539999723434448},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.7049999833106995},{"id":"https://openalex.org/keywords/recursive-language-models","display_name":"recursive language models","score":0.6809999942779541},{"id":"https://openalex.org/keywords/open-weight-language-models","display_name":"open-weight language models","score":0.597000002861023},{"id":"https://openalex.org/keywords/tool-calling","display_name":"tool calling","score":0.5220000147819519},{"id":"https://openalex.org/keywords/evidence-management","display_name":"evidence management","score":0.5360000133514404},{"id":"https://openalex.org/keywords/question-structure","display_name":"question structure","score":0.3869999945163727},{"id":"https://openalex.org/keywords/training-data","display_name":"training data","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.6480000019073486},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.06650","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06650","pdf_url":"https://arxiv.org/pdf/2610.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.06650","doi":"https://doi.org/10.48550/arxiv.2610.06650","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.06650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.06650","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06650","pdf_url":"https://arxiv.org/pdf/2610.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220693231.pdf","grobid_xml":"https://content.openalex.org/works/W7220693231.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2080133951","https://openalex.org/W2980401255","https://openalex.org/W3100058503","https://openalex.org/W4304195432","https://openalex.org/W4310695914","https://openalex.org/W4385570777","https://openalex.org/W4391555701","https://openalex.org/W4394778349","https://openalex.org/W4412945508","https://openalex.org/W4414597364","https://openalex.org/W4416683608","https://openalex.org/W4417485409","https://openalex.org/W6891936057","https://openalex.org/W7094459024","https://openalex.org/W7129373530","https://openalex.org/W7155622066","https://openalex.org/W7164571323","https://openalex.org/W7168365161","https://openalex.org/W7171646184"],"related_works":["https://openalex.org/W7170093949","https://openalex.org/W7148987599","https://openalex.org/W7134190854","https://openalex.org/W7222209921","https://openalex.org/W7167931267","https://openalex.org/W7125352563","https://openalex.org/W7120460935","https://openalex.org/W7213624723","https://openalex.org/W7140074174","https://openalex.org/W7155494983"],"abstract_inverted_index":{"Wikidata":[0,158],"is":[1,44,130,181],"one":[2],"of":[3,70,97,106,119],"the":[4,23,59,68,87,95,104,120,135,172,195,225,241],"largest":[5],"open":[6],"knowledge":[7],"bases,":[8],"yet":[9],"answering":[10],"a":[11,18,35,75,107,141,156,263],"complex":[12],"question":[13,108],"over":[14,188,240],"it":[15],"still":[16],"requires":[17],"SPARQL":[19],"query":[20],"that":[21,54,63,80,94,117,171,177,201],"names":[22],"right":[24],"entities":[25,114,163],"and":[26,28,61,78,138,176,190,216,256],"properties":[27],"chains":[29],"their":[30],"relations.":[31],"Language":[32],"models":[33,145,206,229],"offer":[34],"natural-language":[36],"alternative":[37],"but":[38],"answer":[39,56],"largely":[40],"from":[41,126,134,246,266],"memory,":[42],"which":[43,205],"least":[45],"reliable":[46],"for":[47],"less":[48],"prominent":[49],"entities.":[50],"We":[51,90,151,183],"study":[52],"agents":[53],"instead":[55],"by":[57,160],"exploring":[58],"graph,":[60],"argue":[62],"two":[64],"obstacles":[65],"limit":[66],"them:":[67],"lack":[69],"training":[71],"data":[72],"recording":[73],"how":[74,127],"solver":[76],"explores,":[77],"interfaces":[79,234],"add":[81],"large":[82],"graph":[83,98,208],"results":[84,211],"directly":[85],"to":[86,248,268],"model's":[88],"context.":[89],"test":[91],"three":[92],"hypotheses:":[93],"difficulty":[96],"search":[99,124],"can":[100,146],"be":[101],"controlled":[102],"through":[103,112,220],"structure":[105],"rather":[109,132],"than":[110,133],"only":[111],"obscure":[113],"or":[115],"wording;":[116],"much":[118],"failure":[121],"on":[122,155,262],"long-horizon":[123],"comes":[125],"retrieved":[128],"evidence":[129,219],"managed":[131],"model":[136,198,260],"itself;":[137],"that,":[139],"in":[140,204,212],"suitable":[142],"environment,":[143],"open-weight":[144,259],"match":[147],"commercial":[148],"closed":[149],"ones.":[150],"construct":[152],"multi-hop":[153,191,254],"questions":[154],"frozen":[157],"snapshot":[159],"replacing":[161],"named":[162],"with":[164,194,236],"nested":[165],"conditions,":[166],"checking":[167],"after":[168],"each":[169],"expansion":[170],"target":[173],"remains":[174],"unique":[175],"every":[178],"new":[179],"condition":[180],"necessary.":[182],"release":[184],"10,235":[185],"solving":[186],"traces":[187],"single-entity":[189],"questions,":[192,224],"together":[193],"recursive":[196],"language":[197],"(RLM)":[199],"harness":[200,226],"produced":[202],"them,":[203],"batch":[207],"calls,":[209],"keep":[210],"persistent":[213],"Python":[214],"state":[215],"interpret":[217],"selected":[218],"sub-calls.":[221],"On":[222],"100":[223],"improves":[227],"both":[228,233],"we":[230],"ran":[231],"under":[232],"compared":[235],"direct":[237],"tool":[238],"calling":[239],"same":[242],"functions:":[243],"gpt-6-luna":[244],"rises":[245],"49":[247],"61":[249],"correct":[250],"answers,":[251],"doubling":[252],"its":[253],"accuracy,":[255],"Qwen3.8-27B,":[257],"an":[258],"served":[261],"single":[264],"GPU,":[265],"60":[267],"74.":[269]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-07T00:00:00"}