{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBMZUVGEGHIV4ZUO5PWHZ3V4DH","short_pith_number":"pith:CBMZUVGE","schema_version":"1.0","canonical_sha256":"10599a54c431d15e668eebec7ceebc19e328b2b8354d423b1b05970dc35f54fd","source":{"kind":"arxiv","id":"2410.09732","version":2},"attestation_state":"computed","paper":{"title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baichuan Zhou, Conghui He, Dahua Lin, Hengrui Kang, Honglin Lin, Junan Zhang, Jun He, Junyan Ye, Tianyi Bai, Tong Wu, Weijia Li, Yiping Chen, Zhizheng Wu, Zihao Wang, Zilong Huang","submitted_at":"2024-10-13T05:26:36Z","abstract_excerpt":"With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data increasingly challenging. Synthetic data detection has thus garnered widespread attention, and the performance of large multimodal models (LMMs) in this task has attracted significant interest. LMMs can provide natural language explanations for their authenticity judgments, enhancing the explainability of synthetic content detection. Simultaneously, the task of distinguishing between real and synthetic data effectively"},"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":"2410.09732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T05:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"7326128294efeb83321ab2212bb5aa16d33c321f9962387c07c5c1e60c257aff","abstract_canon_sha256":"ce0eba0e4aa8e2d4c9e5ad5afd46dd006e6c651ce36e28b41ea8149ccfd509de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:26.392888Z","signature_b64":"bol54UMMPdPEq4RFtCJCuGKDhzb2cQdnMkvUR3Pj2VpyKtyYpEC5Jq+MbeqhdzGVRKqGNOuEyXhzJfDL6nEXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10599a54c431d15e668eebec7ceebc19e328b2b8354d423b1b05970dc35f54fd","last_reissued_at":"2026-07-05T10:51:26.392367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:26.392367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baichuan Zhou, Conghui He, Dahua Lin, Hengrui Kang, Honglin Lin, Junan Zhang, Jun He, Junyan Ye, Tianyi Bai, Tong Wu, Weijia Li, Yiping Chen, Zhizheng Wu, Zihao Wang, Zilong Huang","submitted_at":"2024-10-13T05:26:36Z","abstract_excerpt":"With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data increasingly challenging. Synthetic data detection has thus garnered widespread attention, and the performance of large multimodal models (LMMs) in this task has attracted significant interest. LMMs can provide natural language explanations for their authenticity judgments, enhancing the explainability of synthetic content detection. Simultaneously, the task of distinguishing between real and synthetic data effectively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09732","kind":"arxiv","version":2},"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/2410.09732/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":"2410.09732","created_at":"2026-07-05T10:51:26.392433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09732v2","created_at":"2026-07-05T10:51:26.392433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09732","created_at":"2026-07-05T10:51:26.392433+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBMZUVGEGHIV","created_at":"2026-07-05T10:51:26.392433+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBMZUVGEGHIV4ZUO","created_at":"2026-07-05T10:51:26.392433+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBMZUVGE","created_at":"2026-07-05T10:51:26.392433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11200","citing_title":"Detecting AI-Generated Content on Social Media with Multi-modal Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12671","citing_title":"SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27348","citing_title":"When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21977","citing_title":"Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10248","citing_title":"RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13281","citing_title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH","json":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH.json","graph_json":"https://pith.science/api/pith-number/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/graph.json","events_json":"https://pith.science/api/pith-number/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/events.json","paper":"https://pith.science/paper/CBMZUVGE"},"agent_actions":{"view_html":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH","download_json":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH.json","view_paper":"https://pith.science/paper/CBMZUVGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09732&json=true","fetch_graph":"https://pith.science/api/pith-number/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/graph.json","fetch_events":"https://pith.science/api/pith-number/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/action/storage_attestation","attest_author":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/action/author_attestation","sign_citation":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/action/citation_signature","submit_replication":"https://pith.science/pith/CBMZUVGEGHIV4ZUO5PWHZ3V4DH/action/replication_record"}},"created_at":"2026-07-05T10:51:26.392433+00:00","updated_at":"2026-07-05T10:51:26.392433+00:00"}