{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TM5UKONJYKJB2FU35NXZ33SOQE","short_pith_number":"pith:TM5UKONJ","schema_version":"1.0","canonical_sha256":"9b3b4539a9c2921d169beb6f9dee4e810175b38c27f9d85289f2c72844c23a11","source":{"kind":"arxiv","id":"2402.08200","version":1},"attestation_state":"computed","paper":{"title":"Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AprilPyone MaungMaung, Hitoshi Kiya, Huy H. Nguyen, Isao Echizen","submitted_at":"2024-02-13T03:55:09Z","abstract_excerpt":"We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale dataset like ImageNet and introduces Spurious ImageNet, we found that not all spurious images are spurious across different classifiers. Although spurious images help measure the reliance of a classifier, filtering many images from the Internet to find more spurious features is time-consuming. To this end, we utilize an existing approach of personalizing large-scale text-to-image diffusion models with available disc"},"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":"2402.08200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-13T03:55:09Z","cross_cats_sorted":[],"title_canon_sha256":"55764a4372ab7c3665814c8af67bb3643bc29015ad280a3ddc9483c7803fd4c1","abstract_canon_sha256":"79af3d7930259f9ac14d8b50f3755ebbe9263ff91191ea055449525660c99e82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:28.778098Z","signature_b64":"ZzCLn8PpFpXlpG3/1/Me8pigXe5CGKtTC9/M1hm4qkux4LgsUp+3Ye9G9sy9M8CntLy4t80jIJfOd6217Q62Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b3b4539a9c2921d169beb6f9dee4e810175b38c27f9d85289f2c72844c23a11","last_reissued_at":"2026-07-05T07:44:28.775924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:28.775924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AprilPyone MaungMaung, Hitoshi Kiya, Huy H. Nguyen, Isao Echizen","submitted_at":"2024-02-13T03:55:09Z","abstract_excerpt":"We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale dataset like ImageNet and introduces Spurious ImageNet, we found that not all spurious images are spurious across different classifiers. Although spurious images help measure the reliance of a classifier, filtering many images from the Internet to find more spurious features is time-consuming. To this end, we utilize an existing approach of personalizing large-scale text-to-image diffusion models with available disc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08200","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/2402.08200/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":"2402.08200","created_at":"2026-07-05T07:44:28.775981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08200v1","created_at":"2026-07-05T07:44:28.775981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08200","created_at":"2026-07-05T07:44:28.775981+00:00"},{"alias_kind":"pith_short_12","alias_value":"TM5UKONJYKJB","created_at":"2026-07-05T07:44:28.775981+00:00"},{"alias_kind":"pith_short_16","alias_value":"TM5UKONJYKJB2FU3","created_at":"2026-07-05T07:44:28.775981+00:00"},{"alias_kind":"pith_short_8","alias_value":"TM5UKONJ","created_at":"2026-07-05T07:44:28.775981+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/TM5UKONJYKJB2FU35NXZ33SOQE","json":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE.json","graph_json":"https://pith.science/api/pith-number/TM5UKONJYKJB2FU35NXZ33SOQE/graph.json","events_json":"https://pith.science/api/pith-number/TM5UKONJYKJB2FU35NXZ33SOQE/events.json","paper":"https://pith.science/paper/TM5UKONJ"},"agent_actions":{"view_html":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE","download_json":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE.json","view_paper":"https://pith.science/paper/TM5UKONJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08200&json=true","fetch_graph":"https://pith.science/api/pith-number/TM5UKONJYKJB2FU35NXZ33SOQE/graph.json","fetch_events":"https://pith.science/api/pith-number/TM5UKONJYKJB2FU35NXZ33SOQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE/action/storage_attestation","attest_author":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE/action/author_attestation","sign_citation":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE/action/citation_signature","submit_replication":"https://pith.science/pith/TM5UKONJYKJB2FU35NXZ33SOQE/action/replication_record"}},"created_at":"2026-07-05T07:44:28.775981+00:00","updated_at":"2026-07-05T07:44:28.775981+00:00"}