{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JT2GF5YQ36DJRJTE7L2SKXWKDJ","short_pith_number":"pith:JT2GF5YQ","canonical_record":{"source":{"id":"2305.13257","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-22T17:28:00Z","cross_cats_sorted":[],"title_canon_sha256":"60bc7758bd08cc46d950d380e3ec947c307a6572848037989f45c9b58fef5be5","abstract_canon_sha256":"e47ddf975125b16e8b5a3af5af5e2461967ca34ecbc4a7bb04f5830263ed4118"},"schema_version":"1.0"},"canonical_sha256":"4cf462f710df8698a664faf5255eca1a4cf206073b793dedbbd04f1abcef996b","source":{"kind":"arxiv","id":"2305.13257","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13257","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13257v4","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13257","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"JT2GF5YQ36DJ","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"JT2GF5YQ36DJRJTE","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"JT2GF5YQ","created_at":"2026-07-05T08:43:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JT2GF5YQ36DJRJTE7L2SKXWKDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13257","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-22T17:28:00Z","cross_cats_sorted":[],"title_canon_sha256":"60bc7758bd08cc46d950d380e3ec947c307a6572848037989f45c9b58fef5be5","abstract_canon_sha256":"e47ddf975125b16e8b5a3af5af5e2461967ca34ecbc4a7bb04f5830263ed4118"},"schema_version":"1.0"},"canonical_sha256":"4cf462f710df8698a664faf5255eca1a4cf206073b793dedbbd04f1abcef996b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:22.221391Z","signature_b64":"CUnACR6VG76vkDc2qBwkGIc9h3EpT4JPkXiHRoeHpAUQct59QnYyHEA1EoRH7ITOABm4kjmkcUqPACKLYBy0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cf462f710df8698a664faf5255eca1a4cf206073b793dedbbd04f1abcef996b","last_reissued_at":"2026-07-05T08:43:22.220968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:22.220968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13257","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdWpyL2E57n1quO9M6hB8xElrtJMqTOQDW42b8oXVhcqXGxC9iUqxbsjTOckPAMcyV6Ru7FWLnXKcd3H5Uo3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:14:52.949594Z"},"content_sha256":"6334fbe74463b55707c9363ea49bb2e561a084eb5578b057e2afb657469d9d90","schema_version":"1.0","event_id":"sha256:6334fbe74463b55707c9363ea49bb2e561a084eb5578b057e2afb657469d9d90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JT2GF5YQ36DJRJTE7L2SKXWKDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Watermarking Text Data on Large Language Models for Dataset Copyright","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hongsheng Hu, Lichao Sun, Xun Chen, Xuyun Zhang, Yixin Liu","submitted_at":"2023-05-22T17:28:00Z","abstract_excerpt":"Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also vulnerable to various privacy attacks, while much sensitive information exists in the training dataset. The attacker can easily steal sensitive information from public models, e.g., individuals' email addresses and phone numbers. In an attempt to address these issues, particularly the unauthorized use of private data, we introduce a novel watermarking technique v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13257","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/2305.13257/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":"2026-07-05T08:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skjl/eIl9fQC97tuxl+iIlLONBnSgKLbFuXzCRW9a0U4uvAbisSPR88TY2wCF0YSHi2dDz3ZOtyd9A8Tp8qDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:14:52.949925Z"},"content_sha256":"69360690fa8ec4f359c19c105260c392fd914f8866efcd8012f20e671a74c59f","schema_version":"1.0","event_id":"sha256:69360690fa8ec4f359c19c105260c392fd914f8866efcd8012f20e671a74c59f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/bundle.json","state_url":"https://pith.science/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/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":"2026-08-18T17:14:52Z","links":{"resolver":"https://pith.science/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ","bundle":"https://pith.science/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/bundle.json","state":"https://pith.science/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JT2GF5YQ36DJRJTE7L2SKXWKDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JT2GF5YQ36DJRJTE7L2SKXWKDJ","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":"e47ddf975125b16e8b5a3af5af5e2461967ca34ecbc4a7bb04f5830263ed4118","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-22T17:28:00Z","title_canon_sha256":"60bc7758bd08cc46d950d380e3ec947c307a6572848037989f45c9b58fef5be5"},"schema_version":"1.0","source":{"id":"2305.13257","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13257","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13257v4","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13257","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"JT2GF5YQ36DJ","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"JT2GF5YQ36DJRJTE","created_at":"2026-07-05T08:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"JT2GF5YQ","created_at":"2026-07-05T08:43:22Z"}],"graph_snapshots":[{"event_id":"sha256:69360690fa8ec4f359c19c105260c392fd914f8866efcd8012f20e671a74c59f","target":"graph","created_at":"2026-07-05T08:43:22Z","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/2305.13257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also vulnerable to various privacy attacks, while much sensitive information exists in the training dataset. The attacker can easily steal sensitive information from public models, e.g., individuals' email addresses and phone numbers. In an attempt to address these issues, particularly the unauthorized use of private data, we introduce a novel watermarking technique v","authors_text":"Hongsheng Hu, Lichao Sun, Xun Chen, Xuyun Zhang, Yixin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-22T17:28:00Z","title":"Watermarking Text Data on Large Language Models for Dataset Copyright"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13257","kind":"arxiv","version":4},"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":"sha256:6334fbe74463b55707c9363ea49bb2e561a084eb5578b057e2afb657469d9d90","target":"record","created_at":"2026-07-05T08:43:22Z","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":"e47ddf975125b16e8b5a3af5af5e2461967ca34ecbc4a7bb04f5830263ed4118","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-22T17:28:00Z","title_canon_sha256":"60bc7758bd08cc46d950d380e3ec947c307a6572848037989f45c9b58fef5be5"},"schema_version":"1.0","source":{"id":"2305.13257","kind":"arxiv","version":4}},"canonical_sha256":"4cf462f710df8698a664faf5255eca1a4cf206073b793dedbbd04f1abcef996b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cf462f710df8698a664faf5255eca1a4cf206073b793dedbbd04f1abcef996b","first_computed_at":"2026-07-05T08:43:22.220968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:22.220968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUnACR6VG76vkDc2qBwkGIc9h3EpT4JPkXiHRoeHpAUQct59QnYyHEA1EoRH7ITOABm4kjmkcUqPACKLYBy0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:22.221391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13257","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6334fbe74463b55707c9363ea49bb2e561a084eb5578b057e2afb657469d9d90","sha256:69360690fa8ec4f359c19c105260c392fd914f8866efcd8012f20e671a74c59f"],"state_sha256":"ef22c43cbda28f5539b35f03457c94ec57ca8be54a5c03cb9a79524b3102cc0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O1kKch/o95y3spuVog6cB5U18EM3uznWwdyz4eKdvVn4/jyDulJR5EYhlR8Pf5FkpDACORiQZf45Ikhiq5vwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:14:52.953301Z","bundle_sha256":"b751060aae54d8201e63292fc4708ac0d0d5dbed8fe5884ef9afbe22f43eef76"}}