{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MM34KEOBDBNULMQ677TVM6UH7P","short_pith_number":"pith:MM34KEOB","schema_version":"1.0","canonical_sha256":"6337c511c1185b45b21effe7567a87fbc64ab1a3a608fddb5e24949756ef1398","source":{"kind":"arxiv","id":"2507.03034","version":4},"attestation_state":"computed","paper":{"title":"Rethinking Data Protection in the (Generative) Artificial Intelligence Era","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.CY"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Junfeng Guo, Kui Ren, Michael Backes, Philip Torr, Pin-Yu Chen, Shuo Shao, Tianwei Zhang, Yiming Li, Yu He, Zhan Qin","submitted_at":"2025-07-03T02:45:51Z","abstract_excerpt":"The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the AI lifecycle from the training samples that shape model parameters to the prompts and outputs that drive real-world model deployment. This shift renders traditional notions of data protection insufficient, while the boundaries of what needs safeguarding remain poorly defined. Failing to safeguard data in AI systems can inflict societal and individual, underscoring the urgent need to clearly delineate the scope of an"},"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":"2507.03034","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T02:45:51Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV","cs.CY"],"title_canon_sha256":"d2d6b49d62ebed1b02eb091425ce4e4cc665419cf60e00f8d9fac992f59dd5e8","abstract_canon_sha256":"3c94e9321e7d5e5073d661788e5102cb19af4162fc1a05627bf067f026cb6413"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:49.701567Z","signature_b64":"lgqyTKmvAeCPA59c8gJMA9aJ8Wn0BmrTvB6GqcnukRlu0W1sQrLTxP9MUL7hoxsKZcYxtSYP2AlGQrWYWT/+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6337c511c1185b45b21effe7567a87fbc64ab1a3a608fddb5e24949756ef1398","last_reissued_at":"2026-07-05T12:03:49.700904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:49.700904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Data Protection in the (Generative) Artificial Intelligence Era","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.CY"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Junfeng Guo, Kui Ren, Michael Backes, Philip Torr, Pin-Yu Chen, Shuo Shao, Tianwei Zhang, Yiming Li, Yu He, Zhan Qin","submitted_at":"2025-07-03T02:45:51Z","abstract_excerpt":"The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the AI lifecycle from the training samples that shape model parameters to the prompts and outputs that drive real-world model deployment. This shift renders traditional notions of data protection insufficient, while the boundaries of what needs safeguarding remain poorly defined. Failing to safeguard data in AI systems can inflict societal and individual, underscoring the urgent need to clearly delineate the scope of an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03034","kind":"arxiv","version":4},"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/2507.03034/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":"2507.03034","created_at":"2026-07-05T12:03:49.701006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03034v4","created_at":"2026-07-05T12:03:49.701006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03034","created_at":"2026-07-05T12:03:49.701006+00:00"},{"alias_kind":"pith_short_12","alias_value":"MM34KEOBDBNU","created_at":"2026-07-05T12:03:49.701006+00:00"},{"alias_kind":"pith_short_16","alias_value":"MM34KEOBDBNULMQ6","created_at":"2026-07-05T12:03:49.701006+00:00"},{"alias_kind":"pith_short_8","alias_value":"MM34KEOB","created_at":"2026-07-05T12:03:49.701006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07539","citing_title":"Prompt Governance? On Governing Technologies Governed by Natural Language","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29569","citing_title":"LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28890","citing_title":"Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03117","citing_title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2508.02115","citing_title":"Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06774","citing_title":"RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P","json":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P.json","graph_json":"https://pith.science/api/pith-number/MM34KEOBDBNULMQ677TVM6UH7P/graph.json","events_json":"https://pith.science/api/pith-number/MM34KEOBDBNULMQ677TVM6UH7P/events.json","paper":"https://pith.science/paper/MM34KEOB"},"agent_actions":{"view_html":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P","download_json":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P.json","view_paper":"https://pith.science/paper/MM34KEOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03034&json=true","fetch_graph":"https://pith.science/api/pith-number/MM34KEOBDBNULMQ677TVM6UH7P/graph.json","fetch_events":"https://pith.science/api/pith-number/MM34KEOBDBNULMQ677TVM6UH7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P/action/storage_attestation","attest_author":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P/action/author_attestation","sign_citation":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P/action/citation_signature","submit_replication":"https://pith.science/pith/MM34KEOBDBNULMQ677TVM6UH7P/action/replication_record"}},"created_at":"2026-07-05T12:03:49.701006+00:00","updated_at":"2026-07-05T12:03:49.701006+00:00"}