{"id":"https://openalex.org/W7171940224","doi":"https://doi.org/10.48550/arxiv.2607.27726","title":"Baikal: Structured Search for Deep Research over Data Lakes","display_name":"Baikal: Structured Search for Deep Research over Data Lakes","publication_year":2026,"publication_date":"2026-07-30","ids":{"openalex":"https://openalex.org/W7171940224","doi":"https://doi.org/10.48550/arxiv.2607.27726"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.27726","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27726","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.27726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144112871","display_name":"Dhruv Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Dhruv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144141316","display_name":"Rishitha Guttapalle Mohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohan, Rishitha Guttapalle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144176277","display_name":"Aarti Kumari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumari, Aarti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144162367","display_name":"Ashi Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sinha, Ashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144169373","display_name":"Athulya Anil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anil, Athulya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivas, Kavitha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035277014","display_name":"Horst Samulowitz","orcid":"https://orcid.org/0000-0002-6780-3217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samulowitz, Horst","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5144136153","display_name":"Andrew McCallum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McCallum, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.1809999942779541,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.1809999942779541,"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/T14347","display_name":"Big Data and Digital Economy","score":0.07850000262260437,"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/T11719","display_name":"Data Quality and Management","score":0.054999999701976776,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.6298999786376953},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48500001430511475},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.44510000944137573},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.412200003862381},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4027999937534332},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.37929999828338623},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.31690001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3346000015735626},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.27726","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27726","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.27726","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27726","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"research":[1,61,160,186,260],"over":[2,62,85,136,210,263],"data":[3,63,140,195,265],"lakes":[4,64,141],"requires":[5],"an":[6,184],"LLM":[7],"agent":[8,187],"to":[9,19,35,46,88,108,124,175,227],"investigate":[10,36],"evidence":[11,43,79,232],"across":[12],"thousands":[13],"of":[14,254],"heterogeneous":[15,78,264],"tables":[16],"and":[17,28,44,70,91,99,113,121,127,138,144,153,170,172,178,183,190,218,229,237,239,261],"passages":[18,152],"synthesize":[20],"a":[21,52,66,74,163],"report.":[22],"Existing":[23],"methods":[24],"perform":[25],"iterative":[26],"retrieval":[27,189],"generation,":[29],"letting":[30],"accumulated":[31],"context":[32],"determine":[33],"what":[34],"next,":[37],"which":[38,234],"can":[39],"overexploit":[40],"locally":[41],"promising":[42],"fail":[45],"cover":[47],"distinct":[48],"semantic":[49,81,231,256],"regions":[50],"under":[51,116,200,244],"fixed":[53],"budget.":[54,248],"To":[55],"address":[56],"this,":[57],"we":[58],"cast":[59],"deep":[60],"as":[65,106],"budgeted":[67],"search":[68,115],"problem":[69],"present":[71],"Baikal":[72,97,131,177,197],"-":[73],"framework":[75],"that":[76],"clusters":[77],"into":[80],"regions,":[82,233],"then":[83],"searches":[84],"them":[86],"adaptively":[87],"balance":[89],"exploration":[90,257],"exploitation.":[92],"Within":[93],"each":[94,135],"selected":[95],"region,":[96],"generates":[98],"investigates":[100],"region-grounded":[101],"subquestions,":[102],"using":[103],"finding":[104],"quality":[105,161],"rewards":[107],"update":[109],"region-level":[110],"value":[111,253],"estimates":[112],"guide":[114],"policies":[117],"ranging":[118],"from":[119],"random":[120],"LLM-guided":[122],"selection":[123],"Bayesian":[125],"$\u03b5$-greedy":[126],"UCB.":[128],"We":[129,158],"evaluate":[130],"on":[132,216,220],"15":[133],"queries":[134],"HybridQA":[137,217],"TAT-QA":[139],"containing":[142],"10,993":[143],"2,757":[145],"tables,":[146],"respectively,":[147],"together":[148],"with":[149,162,188],"227K":[150],"Wikipedia":[151],"13K":[154],"financial":[155],"report":[156,208],"passages.":[157],"assess":[159],"new":[164],"rubric":[165],"covering":[166],"groundedness,":[167],"relevance,":[168],"diversity,":[169],"utility,":[171],"use":[173],"GPT-5-mini":[174],"score":[176],"strong":[179],"baselines,":[180],"including":[181],"DeepSearcher":[182],"OpenCode":[185],"clustering":[191],"variants.":[192],"Across":[193],"both":[194],"lakes,":[196],"performs":[198],"strongly":[199],"several":[201],"region-selection":[202],"policies;":[203],"its":[204],"best":[205],"configuration":[206],"improves":[207,235],"scores":[209],"the":[211,245,252],"strongest":[212],"baselines":[213],"by":[214],"28%":[215],"36%":[219],"TAT-QA.":[221],"Our":[222],"analyses":[223],"attribute":[224],"these":[225],"gains":[226],"organizing":[228],"exploring":[230],"groundedness":[236],"diversity":[238],"yields":[240],"more":[241],"useful":[242],"findings":[243],"same":[246],"subquestion":[247],"These":[249],"results":[250],"demonstrate":[251],"structured":[255],"for":[258],"systematic":[259],"discovery":[262],"lakes.":[266]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}