{"id":"https://openalex.org/W7138432023","doi":"https://doi.org/10.48550/arxiv.2603.14171","title":"TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference","display_name":"TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138432023","doi":"https://doi.org/10.48550/arxiv.2603.14171"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129750414","display_name":"Patryk Marsza\u0142ek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marsza\u0142ek, Patryk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064829424","display_name":"Tomasz Ku\u015bmierczyk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ku\u015bmierczyk, Tomasz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123243868","display_name":"Marek \u015amieja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u015amieja, Marek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.890500009059906,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.890500009059906,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.01940000057220459,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01640000008046627,"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/anomaly-detection","display_name":"Anomaly detection","score":0.8208000063896179},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.620199978351593},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.6151999831199646},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6044999957084656},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4011000096797943},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3865000009536743},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.37439998984336853}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.678600013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467999815940857},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7463008761405945,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Anomaly":[0],"detection":[1,82,117,209],"for":[2,17,80],"tabular":[3],"data":[4],"has":[5,25,32],"been":[6],"a":[7,14,28,164,172],"long-standing":[8],"unsupervised":[9,87],"learning":[10,20,24],"problem":[11],"that":[12,31,46,85,149,215],"remains":[13],"major":[15],"challenge":[16],"current":[18],"deep":[19],"models.":[21],"Recently,":[22],"in-context":[23,52,78,115,218],"emerged":[26],"as":[27,55,163,200,202,221],"new":[29],"paradigm":[30],"shifted":[33],"efforts":[34],"from":[35],"task-specific":[36,229],"optimization":[37],"to":[38,70,89,102,140,227],"large-scale":[39],"pretraining":[40,121],"aimed":[41],"at":[42],"creating":[43],"foundation":[44],"models":[45,79,219],"generalize":[47],"across":[48],"diverse":[49],"datasets.":[50],"Although":[51],"models,":[53],"such":[54,220],"TabPFN,":[56],"perform":[57],"well":[58,201],"in":[59,95,100,171,187],"supervised":[60],"problems,":[61],"their":[62],"learned":[63],"classification-based":[64],"priors":[65],"may":[66],"not":[67],"readily":[68],"extend":[69],"anomaly":[71,81,116,147,169,194,198],"detection.":[72],"In":[73,138],"this":[74],"paper,":[75],"we":[76,181],"study":[77],"and":[83,111,129,189,196],"show":[84,214],"the":[86,103,158,183,203],"extensions":[88],"TabPFN":[90],"exhibit":[91],"unstable":[92],"behavior,":[93],"particularly":[94],"noisy":[96,190],"or":[97,155],"contaminated":[98],"contexts,":[99],"addition":[101],"high":[104],"computational":[105],"cost.":[106],"We":[107],"address":[108],"these":[109],"challenges":[110],"introduce":[112],"TACTIC,":[113],"an":[114],"approach":[118],"based":[119],"on":[120,178,208],"with":[122,192],"anomaly-centric":[123,217],"synthetic":[124],"priors,":[125],"which":[126,144],"provides":[127],"fast":[128],"data-dependent":[130],"reasoning":[131],"about":[132],"anomalies":[133],"while":[134],"avoiding":[135],"dataset-specific":[136],"tuning.":[137],"contrast":[139],"typical":[141],"score-based":[142],"approaches,":[143],"produce":[145],"uncalibrated":[146],"scores":[148],"require":[150],"post-processing":[151],"(e.g.":[152],"threshold":[153],"selection":[154],"ranking":[156],"heuristics),":[157],"proposed":[159],"model":[160],"is":[161],"trained":[162],"discriminative":[165],"predictor,":[166],"enabling":[167],"unambiguous":[168],"decisions":[170],"single":[173],"forward":[174],"pass.":[175],"Through":[176],"experiments":[177,212],"real-world":[179],"datasets,":[180],"examine":[182],"performance":[184],"of":[185,205],"TACTIC":[186,222],"clean":[188],"contexts":[191],"varying":[193],"rates":[195],"different":[197],"types,":[199],"impact":[204],"prior":[206],"choices":[207],"quality.":[210],"Our":[211],"clearly":[213],"specialized":[216],"are":[223],"highly":[224],"competitive":[225],"compared":[226],"other":[228],"methods.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}