{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KSI33C4H37MW74M6U3ML4FMEVA","short_pith_number":"pith:KSI33C4H","schema_version":"1.0","canonical_sha256":"5491bd8b87dfd96ff19ea6d8be1584a81269efed22bcf3455e557e08dc88855d","source":{"kind":"arxiv","id":"2406.04906","version":3},"attestation_state":"computed","paper":{"title":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Liting Huang, Shoujin Wang, Xiyue Zhou, Yiran Zhang, Zhihao Zhang","submitted_at":"2024-06-07T12:58:14Z","abstract_excerpt":"The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The machine-generated content is a double-edged sword. On one hand, it can benefit the society when used appropriately. On the other hand, it may mislead people, posing threats to the society, especially when mixed together with natural content created by humans. Hence, there is an urgent need to develop effective methods to detect machine-generated content. However, the lack of aligned multimodal datasets inhibited the de"},"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":"2406.04906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T12:58:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"012801b64c5c2502feb68a6ac0b2598f6d1be03d670c7657f9d4873717b7b008","abstract_canon_sha256":"3c2609080fa4de6d3d377e9ce56f8bfbe24ff45e15c3ec6899b90fa4cc170c12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:43.964890Z","signature_b64":"bOV7xyP7k6htnnHLvMds0qK0wPwC/zma7g8V5qSHkPcO1vZNccClkzB7rRBDLoLBaV8TIiauQ1YOJDJ4Ueh7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5491bd8b87dfd96ff19ea6d8be1584a81269efed22bcf3455e557e08dc88855d","last_reissued_at":"2026-07-05T10:15:43.964382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:43.964382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Liting Huang, Shoujin Wang, Xiyue Zhou, Yiran Zhang, Zhihao Zhang","submitted_at":"2024-06-07T12:58:14Z","abstract_excerpt":"The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The machine-generated content is a double-edged sword. On one hand, it can benefit the society when used appropriately. On the other hand, it may mislead people, posing threats to the society, especially when mixed together with natural content created by humans. Hence, there is an urgent need to develop effective methods to detect machine-generated content. However, the lack of aligned multimodal datasets inhibited the de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04906","kind":"arxiv","version":3},"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/2406.04906/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":"2406.04906","created_at":"2026-07-05T10:15:43.964435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04906v3","created_at":"2026-07-05T10:15:43.964435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04906","created_at":"2026-07-05T10:15:43.964435+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSI33C4H37MW","created_at":"2026-07-05T10:15:43.964435+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSI33C4H37MW74M6","created_at":"2026-07-05T10:15:43.964435+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSI33C4H","created_at":"2026-07-05T10:15:43.964435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11916","citing_title":"Generating with Fairness: A Modality-Diffused Counterfactual Framework for Incomplete Multimodal Recommendations","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA","json":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA.json","graph_json":"https://pith.science/api/pith-number/KSI33C4H37MW74M6U3ML4FMEVA/graph.json","events_json":"https://pith.science/api/pith-number/KSI33C4H37MW74M6U3ML4FMEVA/events.json","paper":"https://pith.science/paper/KSI33C4H"},"agent_actions":{"view_html":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA","download_json":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA.json","view_paper":"https://pith.science/paper/KSI33C4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04906&json=true","fetch_graph":"https://pith.science/api/pith-number/KSI33C4H37MW74M6U3ML4FMEVA/graph.json","fetch_events":"https://pith.science/api/pith-number/KSI33C4H37MW74M6U3ML4FMEVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA/action/storage_attestation","attest_author":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA/action/author_attestation","sign_citation":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA/action/citation_signature","submit_replication":"https://pith.science/pith/KSI33C4H37MW74M6U3ML4FMEVA/action/replication_record"}},"created_at":"2026-07-05T10:15:43.964435+00:00","updated_at":"2026-07-05T10:15:43.964435+00:00"}