{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DB4U3THOHOOE6WTT5XMBZ7V7NF","short_pith_number":"pith:DB4U3THO","schema_version":"1.0","canonical_sha256":"18794dccee3b9c4f5a73edd81cfebf69565aaf31d39b570cc117afe6dd239bfc","source":{"kind":"arxiv","id":"2506.13780","version":1},"attestation_state":"computed","paper":{"title":"Hidden Bias in the Machine: Stereotypes in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Sedat Porikli, Vedat Porikli","submitted_at":"2025-06-09T23:06:04Z","abstract_excerpt":"Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To investigate these issues, we curated a diverse set of prompts spanning thematic categories such as occupations, traits, actions, ideologies, emotions, family roles, place descriptions, spirituality, and life events. For each of the 160 unique topics, we crafted multiple prompt variations to reflect a wide range of meanings and perspectives. Using Stable Diffusi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.13780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T23:06:04Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"3052c6265a09c45f151d8de2e222b08d60133df73c000c7d68f502365040a35e","abstract_canon_sha256":"4eca90853c482a31286a31ef2d760775260349bce69ebba1dacc1c1ba8c34f03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:43.254112Z","signature_b64":"KYGJML7lZs42lD1XXUQVm1BZ0YgSyB3EprNJ+A5VM14xmVz79CD1zRe4W5fLcEsqVGd6/2xohIX2O32fR/tNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18794dccee3b9c4f5a73edd81cfebf69565aaf31d39b570cc117afe6dd239bfc","last_reissued_at":"2026-07-05T11:22:43.253634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:43.253634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hidden Bias in the Machine: Stereotypes in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Sedat Porikli, Vedat Porikli","submitted_at":"2025-06-09T23:06:04Z","abstract_excerpt":"Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To investigate these issues, we curated a diverse set of prompts spanning thematic categories such as occupations, traits, actions, ideologies, emotions, family roles, place descriptions, spirituality, and life events. For each of the 160 unique topics, we crafted multiple prompt variations to reflect a wide range of meanings and perspectives. Using Stable Diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13780","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.13780/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.13780","created_at":"2026-07-05T11:22:43.253689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13780v1","created_at":"2026-07-05T11:22:43.253689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13780","created_at":"2026-07-05T11:22:43.253689+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB4U3THOHOOE","created_at":"2026-07-05T11:22:43.253689+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB4U3THOHOOE6WTT","created_at":"2026-07-05T11:22:43.253689+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB4U3THO","created_at":"2026-07-05T11:22:43.253689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF","json":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF.json","graph_json":"https://pith.science/api/pith-number/DB4U3THOHOOE6WTT5XMBZ7V7NF/graph.json","events_json":"https://pith.science/api/pith-number/DB4U3THOHOOE6WTT5XMBZ7V7NF/events.json","paper":"https://pith.science/paper/DB4U3THO"},"agent_actions":{"view_html":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF","download_json":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF.json","view_paper":"https://pith.science/paper/DB4U3THO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13780&json=true","fetch_graph":"https://pith.science/api/pith-number/DB4U3THOHOOE6WTT5XMBZ7V7NF/graph.json","fetch_events":"https://pith.science/api/pith-number/DB4U3THOHOOE6WTT5XMBZ7V7NF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF/action/storage_attestation","attest_author":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF/action/author_attestation","sign_citation":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF/action/citation_signature","submit_replication":"https://pith.science/pith/DB4U3THOHOOE6WTT5XMBZ7V7NF/action/replication_record"}},"created_at":"2026-07-05T11:22:43.253689+00:00","updated_at":"2026-07-05T11:22:43.253689+00:00"}