{"id":"https://openalex.org/W7166797015","doi":"https://doi.org/10.18653/v1/2026.acl-short.65","title":"Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study","display_name":"Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166797015","doi":"https://doi.org/10.18653/v1/2026.acl-short.65"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-short.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.65","pdf_url":"https://aclanthology.org/2026.acl-short.65.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-short.65.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120638326","display_name":"Ali El Lahib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali El Lahib","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045424825","display_name":"Ying-Jieh Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying-Jieh Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139716550","display_name":"Zehan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139759609","display_name":"Yuxuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067167426","display_name":"Xinyu Pi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Pi","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83801638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5529999732971191,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.5529999732971191,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.3538999855518341,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0066999997943639755,"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/leakage","display_name":"Leakage (economics)","score":0.504800021648407},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.28700000047683716},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.24449999630451202},{"id":"https://openalex.org/keywords/technology-forecasting","display_name":"Technology forecasting","score":0.24240000545978546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5376999974250793},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24449999630451202},{"id":"https://openalex.org/C161657586","wikidata":"https://www.wikidata.org/wiki/Q1203326","display_name":"Technology forecasting","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2354000061750412},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.22840000689029694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-short.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.65","pdf_url":"https://aclanthology.org/2026.acl-short.65.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-short.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.65","pdf_url":"https://aclanthology.org/2026.acl-short.65.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166797015.pdf","grobid_xml":"https://content.openalex.org/works/W7166797015.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Search-engine":[0],"date":[1],"filters":[2],"are":[3],"widely":[4],"used":[5],"to":[6,69],"enforce":[7],"pre-cutoff":[8],"retrieval":[9,118],"in":[10],"retrospective":[11,114],"evaluations":[12],"of":[13,49],"search-augmented":[14],"forecasters.We":[15],"show":[16],"this":[17],"approach":[18],"is":[19,60,110],"unreliable":[20,97],"across":[21],"two":[22],"major":[23,44],"search":[24,106],"engines:":[25],"auditing":[26],"Google":[27,52],"Search's":[28],"before:":[29],"filter":[30],"and":[31,53,57,65,99,102],"DuckDuckGo's":[32],"date-range":[33],"filter,":[34],"we":[35,75],"find":[36],"that":[37,104],"at":[38],"least":[39],"one":[40],"retrieved":[41],"page":[42],"contains":[43],"post-cutoff":[45],"leakage":[46,90],"for":[47,63,112],"71%":[48],"questions":[50],"on":[51,55,107,122],"81%":[54],"DuckDuckGo,":[56],"the":[58],"answer":[59],"directly":[61],"revealed":[62],"41%":[64],"55%,":[66],"respectively.Using":[67],"gpt-oss-120b":[68],"forecast":[70],"with":[71,85],"these":[72,108],"leaky":[73],"documents,":[74],"demonstrate":[76],"inflated":[77],"prediction":[78],"accuracy":[79],"(Brier":[80],"score":[81],"0.10":[82],"vs.":[83],"0.24":[84],"leak-free":[86],"documents).We":[87],"characterize":[88],"recurring":[89],"mechanisms,":[91],"including":[92],"updated":[93],"articles,":[94],"related-content":[95],"modules,":[96],"metadata,":[98],"absence-based":[100],"signals,":[101],"argue":[103],"date-restricted":[105],"engines":[109],"insufficient":[111],"credible":[113],"evaluation.We":[115],"recommend":[116],"stronger":[117],"safeguards":[119],"or":[120],"evaluation":[121],"frozen,":[123],"time-stamped":[124],"web":[125],"snapshots.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}