{"id":"https://openalex.org/W7214069722","doi":"https://doi.org/10.48550/arxiv.2609.26707","title":"Optimal Expert Annotation for Evaluating Sequential Decision Policies from Text Records","display_name":"Optimal Expert Annotation for Evaluating Sequential Decision Policies from Text Records","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214069722","doi":"https://doi.org/10.48550/arxiv.2609.26707"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.26707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26707","pdf_url":"https://arxiv.org/pdf/2609.26707","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":null,"license_id":null,"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/2609.26707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114414521","display_name":"Woojin Chae","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chae, Woojin","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012190659","display_name":"Ezinne Nwankwo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nwankwo, Ezinne","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113360256","display_name":"Hanqiao Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin, Haitong","raw_affiliation_strings":["University of Washington , Seattle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127818505","display_name":"Angela Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Angela","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5922999978065491,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5922999978065491,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.2152000069618225,"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"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.13369999825954437,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.7860000133514404},{"id":"https://openalex.org/keywords/expert-annotation","display_name":"expert annotation","score":0.7120000123977661},{"id":"https://openalex.org/keywords/doubly-robust-estimation","display_name":"doubly robust estimation","score":0.675000011920929},{"id":"https://openalex.org/keywords/homeless-services","display_name":"homelessness services","score":0.9480000138282776},{"id":"https://openalex.org/keywords/housing-placement","display_name":"housing placement","score":0.9079999923706055},{"id":"https://openalex.org/keywords/human-preference-data","display_name":"human preference data","score":0.5709999799728394},{"id":"https://openalex.org/keywords/estimation-variance","display_name":"estimation variance","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.796999990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402999997138977},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2781400479","wikidata":"https://www.wikidata.org/wiki/Q11640","display_name":"Outreach","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.26707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26707","pdf_url":"https://arxiv.org/pdf/2609.26707","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.26707","doi":"https://doi.org/10.48550/arxiv.2609.26707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.26707","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:2609.26707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26707","pdf_url":"https://arxiv.org/pdf/2609.26707","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214069722.pdf","grobid_xml":"https://content.openalex.org/works/W7214069722.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2969337892","https://openalex.org/W4318908600","https://openalex.org/W4386874982","https://openalex.org/W4391942558","https://openalex.org/W4392539015","https://openalex.org/W4399418230","https://openalex.org/W6891744960","https://openalex.org/W7126027345","https://openalex.org/W7130676567"],"related_works":["https://openalex.org/W7221068585","https://openalex.org/W4405301127","https://openalex.org/W7115607501","https://openalex.org/W3004798888","https://openalex.org/W2953633867","https://openalex.org/W2969337892","https://openalex.org/W3119650156","https://openalex.org/W6889779352","https://openalex.org/W2942437031","https://openalex.org/W7100508246"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,52],"and":[3,28,50,148,168,175,185,201,216,218],"off-policy":[4,86],"evaluation":[5,87],"evaluate":[6],"dynamic":[7],"decision":[8],"rules":[9],"based":[10],"on":[11,176,224],"historical":[12],"data,":[13],"without":[14],"the":[15,104,183],"ability":[16],"to":[17,141],"deploy":[18],"online.":[19],"In":[20,173],"recent":[21],"artificial":[22],"intelligence":[23],"(AI)":[24],"applications,":[25],"simple":[26],"state":[27],"reward":[29],"information":[30],"is":[31,119],"recorded":[32],"as":[33],"complex":[34],"text":[35],"or":[36],"image,":[37],"expert":[38],"annotation":[39,101,215],"may":[40],"be":[41,97,139],"available":[42],"but":[43,59],"at":[44,209,221],"a":[45,66,81,113,122,125,165,206],"higher":[46],"cost.":[47],"Recent":[48],"AI":[49],"machine":[51],"(ML)":[53],"predictors":[54],"can":[55,72,138],"label":[56],"data":[57,95,147],"cheaply":[58],"with":[60,88,124],"unknown":[61],"bias.":[62],"We":[63],"show":[64],"how":[65,155],"limited":[67],"budget":[68,223],"for":[69,84,103,132,198,203],"ground-truth":[70],"data-annotation":[71],"safely":[73],"make":[74],"use":[75],"of":[76,196,211,213],"plentiful":[77],"ML":[78],"predictions":[79],"in":[80,112,170,194],"new":[82,150],"estimator":[83],"doubly-robust":[85],"missing":[89],"rewards.":[90],"Our":[91,117,136],"method":[92,137],"directs":[93],"where":[94],"should":[96],"collected":[98],"by":[99,121,219],"optimizing":[100],"probabilities":[102],"best":[105],"downstream":[106],"estimation":[107],"variance,":[108],"which":[109],"we":[110,191],"implement":[111],"feasible":[114],"batch-adaptive":[115],"approach.":[116],"work":[118],"motivated":[120],"collaboration":[123],"homelessness":[126],"services":[127],"nonprofit":[128,184],"that":[129],"writes":[130],"casenotes":[131,181],"individuals":[133],"over":[134,160],"time.":[135],"used":[140],"unlock":[142],"trustworthy":[143],"inference":[144],"from":[145,182,188],"casenote":[146],"answer":[149],"inferential":[151],"questions":[152],"such":[153],"as:":[154],"does":[156],"expanding":[157],"outreach":[158],"effort":[159],"time":[161],"affect":[162],"progress":[163,204],"towards":[164,205],"housing":[166,171,199,207],"application":[167,208],"improvement":[169],"placement?":[172],"simulations":[174],"two":[177],"real":[178],"datasets":[179],"--":[180,190],"human-preference":[186],"votes":[187],"LMArena":[189,225],"see":[192],"reductions":[193],"RMSE":[195],"37-65%":[197],"placement":[200],"21-67%":[202],"budgets":[210],"50%":[212],"full":[214],"above,":[217],"55-62%":[220],"every":[222],"under":[226],"an":[227],"equal-exposure":[228],"policy.":[229]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-24T00:00:00"}