{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZ7K4EQHWCLQU7OPP4YS7OOPYC","short_pith_number":"pith:SZ7K4EQH","schema_version":"1.0","canonical_sha256":"967eae1207b0970a7dcf7f312fb9cfc08b39aceebc3dcb0473caa782a29def21","source":{"kind":"arxiv","id":"2510.10982","version":2},"attestation_state":"computed","paper":{"title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akide Liu, Derui Wang, Guangdong Bai, Minhui Xue, Shuofeng Liu, Zhiyong Ma, Zhongkui Ma, Zihan Wang","submitted_at":"2025-10-13T03:43:11Z","abstract_excerpt":"Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications. In practice, enforcing this principle remains challenging, as released data can be trivially fed into arbitrary models beyond its declared intent. Existing approaches attempt to mitigate this risk by either perturbing data or retraining models to limit unintended use. These strategies, however, offer no protection against inference by unknown or externally trained models, or "},"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":"2510.10982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T03:43:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"177bf60a3f344ac985901b09f109e12b703f156b933880091e9a421fc867b7b6","abstract_canon_sha256":"6c71442454451efeb7762427462e9cf2c3ca1326278713ba0e27d960f30abc2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:35.319747Z","signature_b64":"7KeZOkDEb25wSg5IPDn30W201565ucyErCCoWIkQtasOvP0FdQXUb89JI+qo6AlcrcVNByuFRo7xe7zm3P63Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"967eae1207b0970a7dcf7f312fb9cfc08b39aceebc3dcb0473caa782a29def21","last_reissued_at":"2026-06-02T01:03:35.318186Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:35.318186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akide Liu, Derui Wang, Guangdong Bai, Minhui Xue, Shuofeng Liu, Zhiyong Ma, Zhongkui Ma, Zihan Wang","submitted_at":"2025-10-13T03:43:11Z","abstract_excerpt":"Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications. In practice, enforcing this principle remains challenging, as released data can be trivially fed into arbitrary models beyond its declared intent. Existing approaches attempt to mitigate this risk by either perturbing data or retraining models to limit unintended use. These strategies, however, offer no protection against inference by unknown or externally trained models, or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10982","kind":"arxiv","version":2},"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/2510.10982/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":"2510.10982","created_at":"2026-06-02T01:03:35.318277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10982v2","created_at":"2026-06-02T01:03:35.318277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10982","created_at":"2026-06-02T01:03:35.318277+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZ7K4EQHWCLQ","created_at":"2026-06-02T01:03:35.318277+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZ7K4EQHWCLQU7OP","created_at":"2026-06-02T01:03:35.318277+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZ7K4EQH","created_at":"2026-06-02T01:03:35.318277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2511.18772","citing_title":"Re-Key-Free, Risky-Free: Adaptable Model Usage Control","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06644","citing_title":"Variational Feature Compression for Model-Specific Representations","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC","json":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC.json","graph_json":"https://pith.science/api/pith-number/SZ7K4EQHWCLQU7OPP4YS7OOPYC/graph.json","events_json":"https://pith.science/api/pith-number/SZ7K4EQHWCLQU7OPP4YS7OOPYC/events.json","paper":"https://pith.science/paper/SZ7K4EQH"},"agent_actions":{"view_html":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC","download_json":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC.json","view_paper":"https://pith.science/paper/SZ7K4EQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10982&json=true","fetch_graph":"https://pith.science/api/pith-number/SZ7K4EQHWCLQU7OPP4YS7OOPYC/graph.json","fetch_events":"https://pith.science/api/pith-number/SZ7K4EQHWCLQU7OPP4YS7OOPYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC/action/storage_attestation","attest_author":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC/action/author_attestation","sign_citation":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC/action/citation_signature","submit_replication":"https://pith.science/pith/SZ7K4EQHWCLQU7OPP4YS7OOPYC/action/replication_record"}},"created_at":"2026-06-02T01:03:35.318277+00:00","updated_at":"2026-06-02T01:03:35.318277+00:00"}