{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VZ3GHZP3ZOOUPHU6IGFHURILT7","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":"bb5b3f04bd0bb35cac42d4d8dad31495322001666a867fa53ed23f7075f6133f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T12:02:57Z","title_canon_sha256":"7571b6e3344f41331d0a0fac526557552760ba76c53622dddb29524aeca1e194"},"schema_version":"1.0","source":{"id":"2310.00646","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00646","created_at":"2026-07-05T09:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00646v2","created_at":"2026-07-05T09:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00646","created_at":"2026-07-05T09:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"VZ3GHZP3ZOOU","created_at":"2026-07-05T09:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"VZ3GHZP3ZOOUPHU6","created_at":"2026-07-05T09:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"VZ3GHZP3","created_at":"2026-07-05T09:11:22Z"}],"graph_snapshots":[{"event_id":"sha256:d5631b8b3c43cf7d7169239334322bb47c3c8237e27279b1bf835edb517082e0","target":"graph","created_at":"2026-07-05T09:11:22Z","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/2310.00646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text by an LLM. In this paper, we show that this problem can be tackled by watermarking, i.e., by enabling an LLM to generate ","authors_text":"Bryan Kian Hsiang Low, Chuan-Sheng Foo, Jingtan Wang, See-kiong Ng, Xinyang Lu, Zhongxiang Dai, Zitong Zhao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T12:02:57Z","title":"Source Attribution for Large Language Model-Generated Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00646","kind":"arxiv","version":2},"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":"sha256:2041d5e7bfbf16d04e6a2d32b4c457b87e0e3bf06a18ee6dd571578e5773d35c","target":"record","created_at":"2026-07-05T09:11:22Z","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":"bb5b3f04bd0bb35cac42d4d8dad31495322001666a867fa53ed23f7075f6133f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T12:02:57Z","title_canon_sha256":"7571b6e3344f41331d0a0fac526557552760ba76c53622dddb29524aeca1e194"},"schema_version":"1.0","source":{"id":"2310.00646","kind":"arxiv","version":2}},"canonical_sha256":"ae7663e5fbcb9d479e9e418a7a450b9feb4abc866c707fbcba25649dd762905c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae7663e5fbcb9d479e9e418a7a450b9feb4abc866c707fbcba25649dd762905c","first_computed_at":"2026-07-05T09:11:22.307257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:22.307257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eckg1mj3wLEy9YuO7oXcn60/ceu7tQOwqfgAKo4SfRL6IajP+17e/IOzkVkx9P531xV0PbLO2+LZnIc7eHYyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:22.307680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00646","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2041d5e7bfbf16d04e6a2d32b4c457b87e0e3bf06a18ee6dd571578e5773d35c","sha256:d5631b8b3c43cf7d7169239334322bb47c3c8237e27279b1bf835edb517082e0"],"state_sha256":"16becdb845c745f39bb2ade87e57a6d0b9e03d1e26e38c1cd9504dba39757a8b"}