{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LNNHWWSTWLHU6VWVACMJZFUBMP","short_pith_number":"pith:LNNHWWST","schema_version":"1.0","canonical_sha256":"5b5a7b5a53b2cf4f56d500989c968163f352755f647d15760455bb179c15bd70","source":{"kind":"arxiv","id":"2608.00716","version":1},"attestation_state":"computed","paper":{"title":"Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Jun Nie, Tongliang Liu, Xinmei Tian, Yiu-ming Cheung, Yonggang Zhang","submitted_at":"2026-08-01T15:33:15Z","abstract_excerpt":"Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, limiting their generalization to unseen distributions. In contrast, large-scale vision models (LVMs) pre-trained on web-scale datasets exhibit exceptional generalization power through exposure to diverse distributions, offering a transformative paradigm for this task. However, our experimental results reveal that LVMs pre-trained on natural-image-dominated data can effectively capture the features of both natural and "},"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":"2608.00716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T15:33:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"339b463584394d4ced6887d4b02c62938c6d28d0b5ef0480ae27acf70561cd45","abstract_canon_sha256":"a4c11207f08f86f7b0cfd64b1e7c946a5dd01a046edd0bf909f61d065be5276b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:54:48.809827Z","signature_b64":"+6Sg/02eFVHttvtVzyahIXtLexd2gBLIf+cPtkQ4WQqzBKAX2JseBgkgLF0nXEk+rWlZxxvASsBPFZwzOpIhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5a7b5a53b2cf4f56d500989c968163f352755f647d15760455bb179c15bd70","last_reissued_at":"2026-08-04T01:54:48.808432Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:54:48.808432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Jun Nie, Tongliang Liu, Xinmei Tian, Yiu-ming Cheung, Yonggang Zhang","submitted_at":"2026-08-01T15:33:15Z","abstract_excerpt":"Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, limiting their generalization to unseen distributions. In contrast, large-scale vision models (LVMs) pre-trained on web-scale datasets exhibit exceptional generalization power through exposure to diverse distributions, offering a transformative paradigm for this task. However, our experimental results reveal that LVMs pre-trained on natural-image-dominated data can effectively capture the features of both natural and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00716","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/2608.00716/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":"2608.00716","created_at":"2026-08-04T01:54:48.809658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00716v1","created_at":"2026-08-04T01:54:48.809658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00716","created_at":"2026-08-04T01:54:48.809658+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNNHWWSTWLHU","created_at":"2026-08-04T01:54:48.809658+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNNHWWSTWLHU6VWV","created_at":"2026-08-04T01:54:48.809658+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNNHWWST","created_at":"2026-08-04T01:54:48.809658+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/LNNHWWSTWLHU6VWVACMJZFUBMP","json":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP.json","graph_json":"https://pith.science/api/pith-number/LNNHWWSTWLHU6VWVACMJZFUBMP/graph.json","events_json":"https://pith.science/api/pith-number/LNNHWWSTWLHU6VWVACMJZFUBMP/events.json","paper":"https://pith.science/paper/LNNHWWST"},"agent_actions":{"view_html":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP","download_json":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP.json","view_paper":"https://pith.science/paper/LNNHWWST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00716&json=true","fetch_graph":"https://pith.science/api/pith-number/LNNHWWSTWLHU6VWVACMJZFUBMP/graph.json","fetch_events":"https://pith.science/api/pith-number/LNNHWWSTWLHU6VWVACMJZFUBMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP/action/storage_attestation","attest_author":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP/action/author_attestation","sign_citation":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP/action/citation_signature","submit_replication":"https://pith.science/pith/LNNHWWSTWLHU6VWVACMJZFUBMP/action/replication_record"}},"created_at":"2026-08-04T01:54:48.809658+00:00","updated_at":"2026-08-04T01:54:48.809658+00:00"}