{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7MT5TXUBSASGUIZQ3PGFFOAQUY","short_pith_number":"pith:7MT5TXUB","schema_version":"1.0","canonical_sha256":"fb27d9de8190246a2330dbcc52b810a61477988a66e7d864c9af74fb79ff6fb6","source":{"kind":"arxiv","id":"2506.13494","version":1},"attestation_state":"computed","paper":{"title":"Watermarking LLM-Generated Datasets in Downstream Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Michael Backes, Tianshuo Cong, Yang Zhang, Yugeng Liu, Zheng Li","submitted_at":"2025-06-16T13:51:49Z","abstract_excerpt":"Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated data to train their models. However, the inability to track content produced by LLMs poses a significant challenge, potentially leading to copyright infringement for the LLM owners. In this paper, we propose a method for injecting watermarks into LLM-generated datasets, enabling the tracking of downstr"},"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":"2506.13494","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-16T13:51:49Z","cross_cats_sorted":[],"title_canon_sha256":"6dbfd4da7abe40891ac7c5db3db7953caa21f4130b226f947b12581e81ef9a3d","abstract_canon_sha256":"61f8d397c3e342f55759137d137f66ded8ac3ca509453a81dc86efd9f231b6b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:20.985189Z","signature_b64":"p+3Bs314Lyn7pgqI9fVcqT0O2YMYSB8QDQcw4eNXkDNRxLhd+B21v5lNHCQkNfBNy32okAziY8sI1ZcD1TAKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb27d9de8190246a2330dbcc52b810a61477988a66e7d864c9af74fb79ff6fb6","last_reissued_at":"2026-07-05T11:22:20.984728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:20.984728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watermarking LLM-Generated Datasets in Downstream Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Michael Backes, Tianshuo Cong, Yang Zhang, Yugeng Liu, Zheng Li","submitted_at":"2025-06-16T13:51:49Z","abstract_excerpt":"Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated data to train their models. However, the inability to track content produced by LLMs poses a significant challenge, potentially leading to copyright infringement for the LLM owners. In this paper, we propose a method for injecting watermarks into LLM-generated datasets, enabling the tracking of downstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13494","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/2506.13494/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":"2506.13494","created_at":"2026-07-05T11:22:20.984786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13494v1","created_at":"2026-07-05T11:22:20.984786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13494","created_at":"2026-07-05T11:22:20.984786+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MT5TXUBSASG","created_at":"2026-07-05T11:22:20.984786+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MT5TXUBSASGUIZQ","created_at":"2026-07-05T11:22:20.984786+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MT5TXUB","created_at":"2026-07-05T11:22:20.984786+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/7MT5TXUBSASGUIZQ3PGFFOAQUY","json":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY.json","graph_json":"https://pith.science/api/pith-number/7MT5TXUBSASGUIZQ3PGFFOAQUY/graph.json","events_json":"https://pith.science/api/pith-number/7MT5TXUBSASGUIZQ3PGFFOAQUY/events.json","paper":"https://pith.science/paper/7MT5TXUB"},"agent_actions":{"view_html":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY","download_json":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY.json","view_paper":"https://pith.science/paper/7MT5TXUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13494&json=true","fetch_graph":"https://pith.science/api/pith-number/7MT5TXUBSASGUIZQ3PGFFOAQUY/graph.json","fetch_events":"https://pith.science/api/pith-number/7MT5TXUBSASGUIZQ3PGFFOAQUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY/action/storage_attestation","attest_author":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY/action/author_attestation","sign_citation":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY/action/citation_signature","submit_replication":"https://pith.science/pith/7MT5TXUBSASGUIZQ3PGFFOAQUY/action/replication_record"}},"created_at":"2026-07-05T11:22:20.984786+00:00","updated_at":"2026-07-05T11:22:20.984786+00:00"}