{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:INWA3V2SAK26CLDAYSRZC22ZSG","short_pith_number":"pith:INWA3V2S","schema_version":"1.0","canonical_sha256":"436c0dd75202b5e12c60c4a3916b59919946700a0713d4f8ec21fd962708003e","source":{"kind":"arxiv","id":"2608.06211","version":1},"attestation_state":"computed","paper":{"title":"Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Binze Wang, Jianqing Li, Jinyu Tian, Xiaochen Yuan, Xingrun Wang","submitted_at":"2026-08-06T16:04:05Z","abstract_excerpt":"Significant advancements in deep learning have been made possible by the utilization of large datasets, underscoring the critical importance of copyright protection. Adding meticulously designed perturbations to examples, making them unlearnable has become a crucial approach for safeguarding data copyright. Existing methods for creating unlearnable examples overlook the risk of data leakage, which can threaten data ownership. Thus, copyright protection in deep learning faces two main threats: illegal model training and malicious data leakage. We investigate that these two threats cannot be sol"},"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":"2608.06211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-08-06T16:04:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d033619b4968438795dc8e5fc53204967f9244ab77dd523d258cb9eb4c2dbb7a","abstract_canon_sha256":"47202e9c62d6aeb47b88715a5b6163f2e66fa13b21a1076bb13e3ea2f87016eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:40:57.396761Z","signature_b64":"VKjeTv8bhSQ//jJ8zOl2TXvHwTqe0jPGOJtwpm0/7LE7mR2pHPw2h6A9zVQJp4tzZH42adLch7Kgeoaah3ylBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436c0dd75202b5e12c60c4a3916b59919946700a0713d4f8ec21fd962708003e","last_reissued_at":"2026-08-07T01:40:57.394939Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:40:57.394939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Binze Wang, Jianqing Li, Jinyu Tian, Xiaochen Yuan, Xingrun Wang","submitted_at":"2026-08-06T16:04:05Z","abstract_excerpt":"Significant advancements in deep learning have been made possible by the utilization of large datasets, underscoring the critical importance of copyright protection. Adding meticulously designed perturbations to examples, making them unlearnable has become a crucial approach for safeguarding data copyright. Existing methods for creating unlearnable examples overlook the risk of data leakage, which can threaten data ownership. Thus, copyright protection in deep learning faces two main threats: illegal model training and malicious data leakage. We investigate that these two threats cannot be sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06211","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/2608.06211/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":"2608.06211","created_at":"2026-08-07T01:40:57.397711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06211v1","created_at":"2026-08-07T01:40:57.397711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06211","created_at":"2026-08-07T01:40:57.397711+00:00"},{"alias_kind":"pith_short_12","alias_value":"INWA3V2SAK26","created_at":"2026-08-07T01:40:57.397711+00:00"},{"alias_kind":"pith_short_16","alias_value":"INWA3V2SAK26CLDA","created_at":"2026-08-07T01:40:57.397711+00:00"},{"alias_kind":"pith_short_8","alias_value":"INWA3V2S","created_at":"2026-08-07T01:40:57.397711+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/INWA3V2SAK26CLDAYSRZC22ZSG","json":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG.json","graph_json":"https://pith.science/api/pith-number/INWA3V2SAK26CLDAYSRZC22ZSG/graph.json","events_json":"https://pith.science/api/pith-number/INWA3V2SAK26CLDAYSRZC22ZSG/events.json","paper":"https://pith.science/paper/INWA3V2S"},"agent_actions":{"view_html":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG","download_json":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG.json","view_paper":"https://pith.science/paper/INWA3V2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06211&json=true","fetch_graph":"https://pith.science/api/pith-number/INWA3V2SAK26CLDAYSRZC22ZSG/graph.json","fetch_events":"https://pith.science/api/pith-number/INWA3V2SAK26CLDAYSRZC22ZSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG/action/storage_attestation","attest_author":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG/action/author_attestation","sign_citation":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG/action/citation_signature","submit_replication":"https://pith.science/pith/INWA3V2SAK26CLDAYSRZC22ZSG/action/replication_record"}},"created_at":"2026-08-07T01:40:57.397711+00:00","updated_at":"2026-08-07T01:40:57.397711+00:00"}