{"id":"https://openalex.org/W4404574201","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1978","title":"PseudoSeer: a Search Engine for Pseudocode","display_name":"PseudoSeer: a Search Engine for Pseudocode","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4404574201","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1978"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1978","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1978","pdf_url":"https://aclanthology.org/2026.findings-acl.1978.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1978.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099083604","display_name":"Levent Toksoz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levent Toksoz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086032910","display_name":"Mukund Srinath","orcid":"https://orcid.org/0009-0007-6474-8199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukund Srinath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102130098","display_name":"Gang Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C. Lee Giles","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":0.00384739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39706","last_page":"39716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.8707000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.8707000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.4533488154411316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33879756927490234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4533488154411316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33879756927490234}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1978","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1978","pdf_url":"https://aclanthology.org/2026.findings-acl.1978.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.12649","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.12649","pdf_url":"https://arxiv.org/pdf/2411.12649","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.12649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.12649","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1978","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1978","pdf_url":"https://aclanthology.org/2026.findings-acl.1978.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404574201.pdf","grobid_xml":"https://content.openalex.org/works/W4404574201.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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":{"PseudoSeer":[0],"is":[1,151],"a":[2,31,60,157,162],"novel":[3],"search":[4,159],"engine":[5],"for":[6,105,164],"academic":[7],"pseudocode,":[8],"enabling":[9],"retrieval":[10,165],"over":[11,77],"320,000":[12],"algorithm":[13],"implementations":[14],"extracted":[15],"from":[16],"the":[17,19,134],"arXiv.Using":[18],"system's":[20],"captionreference":[21],"pairs,":[22,81],"we":[23,82],"study":[24],"asymmetric":[25],"retrieval,":[26],"matching":[27],"short":[28],"queries":[29],"with":[30,49,72,110,129,146],"median":[32],"length":[33],"of":[34,40,46],"five":[35],"words":[36,43],"against":[37],"long":[38],"documents":[39],"roughly":[41],"300":[42],"composed":[44],"primarily":[45],"natural":[47],"language":[48],"limited":[50],"LaTeX":[51],"notation.Our":[52],"evaluation":[53],"reveals":[54],"scaling":[55],"limitations":[56],"in":[57],"embedding":[58,123],"models:":[59],"149M":[61],"parameter":[62,66],"encoder":[63],"outperforms":[64,133],"1.5B":[65],"alternatives,":[67],"while":[68,108],"BM25":[69,147],"remains":[70],"competitive":[71],"pretrained":[73,136],"models.Analyzing":[74],"attention":[75,89,92,104,113,131],"patterns":[76],"33,000":[78],"caption":[79],"document":[80],"identify":[83],"two":[84],"factors":[85],"driving":[86],"these":[87,120],"results:":[88],"efficiency":[90],"and":[91,161],"concentration.Models":[93],"that":[94],"significantly":[95],"attend":[96],"to":[97,115],"sinks":[98],"or":[99],"non-discriminative":[100],"tokens":[101],"leave":[102],"less":[103],"discriminative":[106,117],"content,":[107],"models":[109],"overly":[111],"diffuse":[112],"fail":[114],"form":[116],"representations.Guided":[118],"by":[119,138],"findings,":[121],"PseudoSeer's":[122],"model,":[124],"trained":[125],"via":[126],"contrastive":[127],"learning":[128],"efficient":[130],"patterns,":[132],"best":[135],"model":[137],"8.7":[139],"points.A":[140],"hybrid":[141],"approach":[142],"combining":[143],"learned":[144],"embeddings":[145],"reaches":[148],"66.5%":[149],"R@10.PseudoSeer":[150],"deployed":[152],"at":[153],"pseudoseer.ist.psu.edu":[154],"as":[155],"both":[156],"practical":[158],"system":[160],"benchmark":[163],"evaluation.":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}