{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GTDIOGX74IK6FANKNI7FOB3SHA","short_pith_number":"pith:GTDIOGX7","schema_version":"1.0","canonical_sha256":"34c6871affe215e281aa6a3e570772381181bb04ebcdf61e29e5e1434e846d80","source":{"kind":"arxiv","id":"2512.15693","version":2},"attestation_state":"computed","paper":{"title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Lei Chen, Runze Sun, Wenzhao Zheng, Yanran Zhang, Yifei Li, Yu Zheng","submitted_at":"2025-12-17T18:48:26Z","abstract_excerpt":"The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-T"},"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":"2512.15693","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-17T18:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"6226add8a6c205a10cdc03d15498a96aca8624c9aff044fdb3c492098fa60184","abstract_canon_sha256":"4e4d6d7f9a23fa314e0a4f5406e7d555f10baf3c1d7bd50be8b557080bde42fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:38.113942Z","signature_b64":"m4LwSGvDJlI7Sq3He3JorYKt30q+ezYKTqsDIno1S0bJ9y87/G/jkUQLBmc/gdUM/Z9TYFB4NC6fC6taZHUKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c6871affe215e281aa6a3e570772381181bb04ebcdf61e29e5e1434e846d80","last_reissued_at":"2026-05-20T00:01:38.113241Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:38.113241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Lei Chen, Runze Sun, Wenzhao Zheng, Yanran Zhang, Yifei Li, Yu Zheng","submitted_at":"2025-12-17T18:48:26Z","abstract_excerpt":"The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15693","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/2512.15693/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":"2512.15693","created_at":"2026-05-20T00:01:38.113366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.15693v2","created_at":"2026-05-20T00:01:38.113366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15693","created_at":"2026-05-20T00:01:38.113366+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTDIOGX74IK6","created_at":"2026-05-20T00:01:38.113366+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTDIOGX74IK6FANK","created_at":"2026-05-20T00:01:38.113366+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTDIOGX7","created_at":"2026-05-20T00:01:38.113366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21977","citing_title":"Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA","json":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA.json","graph_json":"https://pith.science/api/pith-number/GTDIOGX74IK6FANKNI7FOB3SHA/graph.json","events_json":"https://pith.science/api/pith-number/GTDIOGX74IK6FANKNI7FOB3SHA/events.json","paper":"https://pith.science/paper/GTDIOGX7"},"agent_actions":{"view_html":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA","download_json":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA.json","view_paper":"https://pith.science/paper/GTDIOGX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.15693&json=true","fetch_graph":"https://pith.science/api/pith-number/GTDIOGX74IK6FANKNI7FOB3SHA/graph.json","fetch_events":"https://pith.science/api/pith-number/GTDIOGX74IK6FANKNI7FOB3SHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA/action/storage_attestation","attest_author":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA/action/author_attestation","sign_citation":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA/action/citation_signature","submit_replication":"https://pith.science/pith/GTDIOGX74IK6FANKNI7FOB3SHA/action/replication_record"}},"created_at":"2026-05-20T00:01:38.113366+00:00","updated_at":"2026-05-20T00:01:38.113366+00:00"}