{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6FUEHWXAPWDSPHWL7HBHTFQF4L","short_pith_number":"pith:6FUEHWXA","schema_version":"1.0","canonical_sha256":"f16843dae07d87279ecbf9c2799605e2d8adcc8eb6489685e214d6d49d839210","source":{"kind":"arxiv","id":"2507.12022","version":1},"attestation_state":"computed","paper":{"title":"Dataset Ownership Verification for Pre-trained Masked Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiarui Duan, Jie Song, Mingli Song, Shengxuming Zhang, Xiaoyan Zhang, Yicheng Shan, Yuanyu Wan, Yuechen Xie","submitted_at":"2025-07-16T08:30:30Z","abstract_excerpt":"High-quality open-source datasets have emerged as a pivotal catalyst driving the swift advancement of deep learning, while facing the looming threat of potential exploitation. Protecting these datasets is of paramount importance for the interests of their owners. The verification of dataset ownership has evolved into a crucial approach in this domain; however, existing verification techniques are predominantly tailored to supervised models and contrastive pre-trained models, rendering them ill-suited for direct application to the increasingly prevalent masked models. In this work, we introduce"},"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":"2507.12022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T08:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"b7498c82308caefdfc080ddb7b9cc60abd5d0fdbec043d708d361ba4257ca97f","abstract_canon_sha256":"ed44812a9d22d56e17945fd77e05525900b31dd4fff3a516718beeb2b01a54bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:13.172611Z","signature_b64":"v84ok9bAVJAId64uKzGVpvQj8KMUwg35ovfYTU4iKp6PqPauBpfztQ9bRYjMy77usRijrBVn66MWh9Wa5UkRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16843dae07d87279ecbf9c2799605e2d8adcc8eb6489685e214d6d49d839210","last_reissued_at":"2026-07-05T11:38:13.172120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:13.172120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Ownership Verification for Pre-trained Masked Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiarui Duan, Jie Song, Mingli Song, Shengxuming Zhang, Xiaoyan Zhang, Yicheng Shan, Yuanyu Wan, Yuechen Xie","submitted_at":"2025-07-16T08:30:30Z","abstract_excerpt":"High-quality open-source datasets have emerged as a pivotal catalyst driving the swift advancement of deep learning, while facing the looming threat of potential exploitation. Protecting these datasets is of paramount importance for the interests of their owners. The verification of dataset ownership has evolved into a crucial approach in this domain; however, existing verification techniques are predominantly tailored to supervised models and contrastive pre-trained models, rendering them ill-suited for direct application to the increasingly prevalent masked models. In this work, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12022","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/2507.12022/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":"2507.12022","created_at":"2026-07-05T11:38:13.172176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12022v1","created_at":"2026-07-05T11:38:13.172176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12022","created_at":"2026-07-05T11:38:13.172176+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FUEHWXAPWDS","created_at":"2026-07-05T11:38:13.172176+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FUEHWXAPWDSPHWL","created_at":"2026-07-05T11:38:13.172176+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FUEHWXA","created_at":"2026-07-05T11:38:13.172176+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/6FUEHWXAPWDSPHWL7HBHTFQF4L","json":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L.json","graph_json":"https://pith.science/api/pith-number/6FUEHWXAPWDSPHWL7HBHTFQF4L/graph.json","events_json":"https://pith.science/api/pith-number/6FUEHWXAPWDSPHWL7HBHTFQF4L/events.json","paper":"https://pith.science/paper/6FUEHWXA"},"agent_actions":{"view_html":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L","download_json":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L.json","view_paper":"https://pith.science/paper/6FUEHWXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12022&json=true","fetch_graph":"https://pith.science/api/pith-number/6FUEHWXAPWDSPHWL7HBHTFQF4L/graph.json","fetch_events":"https://pith.science/api/pith-number/6FUEHWXAPWDSPHWL7HBHTFQF4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L/action/storage_attestation","attest_author":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L/action/author_attestation","sign_citation":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L/action/citation_signature","submit_replication":"https://pith.science/pith/6FUEHWXAPWDSPHWL7HBHTFQF4L/action/replication_record"}},"created_at":"2026-07-05T11:38:13.172176+00:00","updated_at":"2026-07-05T11:38:13.172176+00:00"}