{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JE2UMPGIJXPX2SZ4IGQ3B2IUC6","short_pith_number":"pith:JE2UMPGI","canonical_record":{"source":{"id":"2509.05921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-07T04:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"bf3d4188db30667506fcfb0c93fbe7e846e02377875919bb7388e5026515d8c4","abstract_canon_sha256":"1bea821a8a989b3a4d4b9890c129af4c4e31e0b998a928fe96689d19ffe5bb7e"},"schema_version":"1.0"},"canonical_sha256":"4935463cc84ddf7d4b3c41a1b0e91417b4c0dec7cea075756a022e13041ae132","source":{"kind":"arxiv","id":"2509.05921","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05921","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05921v1","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05921","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"JE2UMPGIJXPX","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"JE2UMPGIJXPX2SZ4","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"JE2UMPGI","created_at":"2026-07-05T12:06:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JE2UMPGIJXPX2SZ4IGQ3B2IUC6","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-07T04:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"bf3d4188db30667506fcfb0c93fbe7e846e02377875919bb7388e5026515d8c4","abstract_canon_sha256":"1bea821a8a989b3a4d4b9890c129af4c4e31e0b998a928fe96689d19ffe5bb7e"},"schema_version":"1.0"},"canonical_sha256":"4935463cc84ddf7d4b3c41a1b0e91417b4c0dec7cea075756a022e13041ae132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:26.569754Z","signature_b64":"d/mkJXN34CT9U4bolIyyHFstbu1SvGv/7vvdsXO5W6gXiRNoyge4cl56/ltz8a8JynkJvBdR6samBBZfdcQxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4935463cc84ddf7d4b3c41a1b0e91417b4c0dec7cea075756a022e13041ae132","last_reissued_at":"2026-07-05T12:06:26.569326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:26.569326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05921","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F1HfeauE7t+W350nsE80CauUuR4T6aDgUXb8kuJLa1JLyYui+bKCf1t2+KTe9Ws3grAJG1GLN3l51gY7vqNLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:33:14.180420Z"},"content_sha256":"71ba5af932357023db3491a3330835a679d99125ca304b870f20e0ba6ff85c4a","schema_version":"1.0","event_id":"sha256:71ba5af932357023db3491a3330835a679d99125ca304b870f20e0ba6ff85c4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JE2UMPGIJXPX2SZ4IGQ3B2IUC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dataset Ownership in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Cheng Wang, Kun Li, Minghui Xu, Xiuzhen Cheng, Yue Zhang","submitted_at":"2025-09-07T04:35:08Z","abstract_excerpt":"As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often fail to address the technical complexities of digital data replication and unauthorized use, particularly in opaque or decentralized environments. This survey provides a comprehensive review of technical approaches for dataset copyright protection, systematically categorizing them into three main classes: non-intrusive methods, which detect unauthorized use without modifying data; minimally-intrusive methods, which em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05921","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/2509.05921/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SU/2RMiKG23BTYIQiTbTIkBonV6tpuILncjnNrhmLbfTlxckP7R1GQofPx9DlBZtJQXQeRgn1LqLEX9nJ6uVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:33:14.181319Z"},"content_sha256":"dd6277e21d1335fca9794d581714d9bbf2ae308982eff5a7111bdcffd539f6e7","schema_version":"1.0","event_id":"sha256:dd6277e21d1335fca9794d581714d9bbf2ae308982eff5a7111bdcffd539f6e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/bundle.json","state_url":"https://pith.science/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T23:33:14Z","links":{"resolver":"https://pith.science/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6","bundle":"https://pith.science/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/bundle.json","state":"https://pith.science/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JE2UMPGIJXPX2SZ4IGQ3B2IUC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JE2UMPGIJXPX2SZ4IGQ3B2IUC6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1bea821a8a989b3a4d4b9890c129af4c4e31e0b998a928fe96689d19ffe5bb7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-07T04:35:08Z","title_canon_sha256":"bf3d4188db30667506fcfb0c93fbe7e846e02377875919bb7388e5026515d8c4"},"schema_version":"1.0","source":{"id":"2509.05921","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05921","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05921v1","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05921","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"JE2UMPGIJXPX","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"JE2UMPGIJXPX2SZ4","created_at":"2026-07-05T12:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"JE2UMPGI","created_at":"2026-07-05T12:06:26Z"}],"graph_snapshots":[{"event_id":"sha256:dd6277e21d1335fca9794d581714d9bbf2ae308982eff5a7111bdcffd539f6e7","target":"graph","created_at":"2026-07-05T12:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.05921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often fail to address the technical complexities of digital data replication and unauthorized use, particularly in opaque or decentralized environments. This survey provides a comprehensive review of technical approaches for dataset copyright protection, systematically categorizing them into three main classes: non-intrusive methods, which detect unauthorized use without modifying data; minimally-intrusive methods, which em","authors_text":"Cheng Wang, Kun Li, Minghui Xu, Xiuzhen Cheng, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-07T04:35:08Z","title":"Dataset Ownership in the Era of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05921","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71ba5af932357023db3491a3330835a679d99125ca304b870f20e0ba6ff85c4a","target":"record","created_at":"2026-07-05T12:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1bea821a8a989b3a4d4b9890c129af4c4e31e0b998a928fe96689d19ffe5bb7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-07T04:35:08Z","title_canon_sha256":"bf3d4188db30667506fcfb0c93fbe7e846e02377875919bb7388e5026515d8c4"},"schema_version":"1.0","source":{"id":"2509.05921","kind":"arxiv","version":1}},"canonical_sha256":"4935463cc84ddf7d4b3c41a1b0e91417b4c0dec7cea075756a022e13041ae132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4935463cc84ddf7d4b3c41a1b0e91417b4c0dec7cea075756a022e13041ae132","first_computed_at":"2026-07-05T12:06:26.569326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:26.569326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d/mkJXN34CT9U4bolIyyHFstbu1SvGv/7vvdsXO5W6gXiRNoyge4cl56/ltz8a8JynkJvBdR6samBBZfdcQxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:26.569754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05921","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71ba5af932357023db3491a3330835a679d99125ca304b870f20e0ba6ff85c4a","sha256:dd6277e21d1335fca9794d581714d9bbf2ae308982eff5a7111bdcffd539f6e7"],"state_sha256":"22c06e1009e677a123fdb10745141a3e4ff452e390d299ffa00aa05c0c85da41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SazU2hNtOHIer0qC+ybR+jeopBf4tCefn4Gf8n6DqJfmY38/RdQGCywZdsIy+BJ0OQLFHASJNwaqOWynydCgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:33:14.186990Z","bundle_sha256":"dcbc98e67884d5b9e274b238cbfea06adff86ea71fad1d2045d9046c9e09fe6e"}}