{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JAVNRII6S5CEUBRLG2LO5MYXWL","short_pith_number":"pith:JAVNRII6","schema_version":"1.0","canonical_sha256":"482ad8a11e97444a062b3696eeb317b2c93964901b4917a85840ef8bf52145ae","source":{"kind":"arxiv","id":"2607.13099","version":1},"attestation_state":"computed","paper":{"title":"WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"L Xiang, Q Jiang, S Sheng, Z Sun","submitted_at":"2026-07-14T06:18:05Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these techniques have rarely been adopted in practice mainly for two reasons: i) severely degraded model performance, and ii) additional inference overhead. To confirm the problem, we construct a comprehensive benchmark spanning different generation tasks to systematically evaluate 9 representative watermarking methods. We found almost all existing methods are designed for text fluency, but not for restr"},"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":"2607.13099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-14T06:18:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"609cc016b0453afedf8997db6b1d3e5a37bffc7bc506b18e80f05759bb980e78","abstract_canon_sha256":"0ea8497fa3798562e512b97a03320134dafe484317a87bc1c45a3df73e7544b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:21:56.335110Z","signature_b64":"RU6q9ygQeHNIAuG4XiY1OfJ+05h/kCLm65WFk5M9i1Xd4pURHwSpi0hOAPLrP73Jvn7PpqNW5YqluoddqdDBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"482ad8a11e97444a062b3696eeb317b2c93964901b4917a85840ef8bf52145ae","last_reissued_at":"2026-07-16T00:21:56.334215Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:21:56.334215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"L Xiang, Q Jiang, S Sheng, Z Sun","submitted_at":"2026-07-14T06:18:05Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these techniques have rarely been adopted in practice mainly for two reasons: i) severely degraded model performance, and ii) additional inference overhead. To confirm the problem, we construct a comprehensive benchmark spanning different generation tasks to systematically evaluate 9 representative watermarking methods. We found almost all existing methods are designed for text fluency, but not for restr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13099","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/2607.13099/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":"2607.13099","created_at":"2026-07-16T00:21:56.334684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13099v1","created_at":"2026-07-16T00:21:56.334684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13099","created_at":"2026-07-16T00:21:56.334684+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAVNRII6S5CE","created_at":"2026-07-16T00:21:56.334684+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAVNRII6S5CEUBRL","created_at":"2026-07-16T00:21:56.334684+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAVNRII6","created_at":"2026-07-16T00:21:56.334684+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/JAVNRII6S5CEUBRLG2LO5MYXWL","json":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL.json","graph_json":"https://pith.science/api/pith-number/JAVNRII6S5CEUBRLG2LO5MYXWL/graph.json","events_json":"https://pith.science/api/pith-number/JAVNRII6S5CEUBRLG2LO5MYXWL/events.json","paper":"https://pith.science/paper/JAVNRII6"},"agent_actions":{"view_html":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL","download_json":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL.json","view_paper":"https://pith.science/paper/JAVNRII6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13099&json=true","fetch_graph":"https://pith.science/api/pith-number/JAVNRII6S5CEUBRLG2LO5MYXWL/graph.json","fetch_events":"https://pith.science/api/pith-number/JAVNRII6S5CEUBRLG2LO5MYXWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL/action/storage_attestation","attest_author":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL/action/author_attestation","sign_citation":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL/action/citation_signature","submit_replication":"https://pith.science/pith/JAVNRII6S5CEUBRLG2LO5MYXWL/action/replication_record"}},"created_at":"2026-07-16T00:21:56.334684+00:00","updated_at":"2026-07-16T00:21:56.334684+00:00"}