{"id":"https://openalex.org/W7225584459","doi":"https://doi.org/10.5281/zenodo.24058595","title":"The Floor Beneath the Filter: Provenance Legibility, Pre-Generative Corpora, and the Limits of Model-Collapse Mitigation","display_name":"The Floor Beneath the Filter: Provenance Legibility, Pre-Generative Corpora, and the Limits of Model-Collapse Mitigation","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225584459","doi":"https://doi.org/10.5281/zenodo.24058595"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24058595","doi":"https://doi.org/10.5281/zenodo.24058595","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24058595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24058595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120913812","display_name":"Josie Jefferson","orcid":"https://orcid.org/0009-0006-3330-8214","observed_orcids":["https://orcid.org/0009-0006-3330-8214"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jefferson, Josie","raw_affiliation_strings":["Unearth Heritage Foundry"],"raw_orcid":"https://orcid.org/0009-0006-3330-8214","affiliations":[{"raw_affiliation_string":"Unearth Heritage Foundry","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120901258","display_name":"Felix Velasco","orcid":"https://orcid.org/0009-0001-6047-0595","observed_orcids":["https://orcid.org/0009-0001-6047-0595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Velasco, Felix","raw_affiliation_strings":["Unearth Heritage Foundry"],"raw_orcid":"https://orcid.org/0009-0001-6047-0595","affiliations":[{"raw_affiliation_string":"Unearth Heritage Foundry","institution_ids":[]}]}],"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6137999892234802,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6137999892234802,"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/T13851","display_name":"Law, AI, and Intellectual Property","score":0.2337999939918518,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.02669999934732914,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/data-provenance","display_name":"data provenance","score":0.8569999933242798},{"id":"https://openalex.org/keywords/synthetic-text","display_name":"synthetic text","score":0.7289999723434448},{"id":"https://openalex.org/keywords/model-collapse","display_name":"model collapse","score":0.7749999761581421},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"digital watermarking","score":0.7269999980926514},{"id":"https://openalex.org/keywords/data-lineage","display_name":"data lineage","score":0.6489999890327454},{"id":"https://openalex.org/keywords/w3c-prov","display_name":"W3C PROV","score":0.8479999899864197},{"id":"https://openalex.org/keywords/ai-infrastructure","display_name":"AI infrastructure","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5981000065803528},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C123890144","wikidata":"https://www.wikidata.org/wiki/Q1975981","display_name":"Vintage","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2778674798","wikidata":"https://www.wikidata.org/wiki/Q632897","display_name":"Digital preservation","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.3165999948978424},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C16635281","wikidata":"https://www.wikidata.org/wiki/Q496098","display_name":"Casting","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2624000012874603},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.24058595","doi":"https://doi.org/10.5281/zenodo.24058595","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24058595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24058596","doi":"https://doi.org/10.5281/zenodo.24058596","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24058596","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24102042","doi":"https://doi.org/10.5281/zenodo.24102042","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24102042","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.24058595","doi":"https://doi.org/10.5281/zenodo.24058595","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24058595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411681065","https://openalex.org/W7161586045","https://openalex.org/W7213037628","https://openalex.org/W7163519629","https://openalex.org/W7216502370","https://openalex.org/W7160645324","https://openalex.org/W7161596787","https://openalex.org/W7171309873","https://openalex.org/W7106322673","https://openalex.org/W7161977752"],"abstract_inverted_index":{"Abstract:":[0],"As":[1],"synthetic":[2,114],"text":[3,55],"saturates":[4],"the":[5,7,11,21,53,98,104,121,125,128],"web,":[6],"ability":[8,48],"to":[9,27,49,82,120],"read":[10],"origin":[12,51,84],"of":[13,95,106,124],"data":[14],"is":[15,43],"collapsing.":[16],"The":[17,47,64,76],"AI":[18,138],"industry":[19],"treats":[20],"collapse":[22],"as":[23,72],"an":[24],"engineering":[25,38,81],"problem":[26],"be":[28],"solved":[29],"with":[30],"filters,":[31],"digital":[32],"watermarks,":[33],"and":[34,90],"secure":[35],"tracking.":[36],"But":[37],"cannot":[39],"manufacture":[40],"provenance;":[41],"it":[42,119],"a":[44,61,73,96],"historical":[45],"state.":[46],"verify":[50],"divides":[52],"world\u2019s":[54],"into":[56],"two":[57],"collections":[58],"separated":[59],"by":[60],"contamination":[62],"event.":[63],"pre-contamination":[65],"corpus":[66,78],"carries":[67],"its":[68],"provenance":[69],"intrinsically,":[70],"acting":[71],"depleting":[74],"reserve.":[75],"post-contamination":[77],"requires":[79],"adversarial":[80],"retain":[83],"certainty.":[85],"All":[86],"mitigation":[87],"strategies\u2014watermarking,":[88],"detection,":[89],"strict":[91],"screening\u2014are":[92],"paid":[93],"reconstructions":[94],"property":[97],"reserve":[99],"had":[100],"for":[101],"free.":[102],"Ultimately,":[103],"future":[105],"artificial":[107],"intelligence":[108],"does":[109],"not":[110],"depend":[111],"on":[112,117],"scaling":[113],"generation,":[115],"but":[116],"anchoring":[118],"unalterable":[122],"record":[123],"time":[126],"before":[127],"imitation":[129],"began.":[130],"Keywords:":[131],"Verifiable":[132],"Origin,":[133],"Model":[134],"Collapse,":[135],"Synthetic":[136],"Data,":[137],"Infrastructure,":[139],"Generative":[140],"Saturation,":[141],"Data":[142,156],"Custody,":[143],"Contamination":[144],"Boundary,":[145],"Depleting":[146],"Reserve,":[147],"Low-Background":[148],"Steel,":[149],"Artificial":[150],"Intelligence,":[151],"Digital":[152],"Archives,":[153],"W3C":[154],"PROV,":[155],"Lineage,":[157],"Machine":[158],"Learning,":[159],"Temporal":[160],"Boundary":[161]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-09T00:00:00"}