{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7D52HLKES66LVOPUBXK2BJO3SU","short_pith_number":"pith:7D52HLKE","schema_version":"1.0","canonical_sha256":"f8fba3ad4497bcbab9f40dd5a0a5db953c2d0ea749045ef6d0fba94c0f6362ea","source":{"kind":"arxiv","id":"2606.04706","version":1},"attestation_state":"computed","paper":{"title":"ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"(2) Ant Group, (3) Hefei University of Technology), Changtao Miao (2), Xiaojing Chen (1), Xinyu Lu (1), Yunfeng Diao (3) ((1) Anhui University","submitted_at":"2026-06-03T10:35:47Z","abstract_excerpt":"AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models. In this paper, we explore reconstruction error as a discriminative forensic cue for AI-generated video detection. By reconstructing input videos with a pretrained WF-VAE, we observe that real and generated videos exhibit distinguishabl"},"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":"2606.04706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T10:35:47Z","cross_cats_sorted":[],"title_canon_sha256":"878025e56e7c7a7cfd5d109d49bd5e7e196f5e8011f79756df1b6a734b689c36","abstract_canon_sha256":"1dc8dde63690e628bf3d571422b0d1c0d07a765ee03d8f3755ac8c582dd6bb66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:25.881363Z","signature_b64":"Tfh535Lzw/FYcNsYZ3leocjSpwQsHZZRGWiZmANIzsJrCSx8Hj/gDYVm+snb43H1hq+Qh8hO7B/xSwIdAtgFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8fba3ad4497bcbab9f40dd5a0a5db953c2d0ea749045ef6d0fba94c0f6362ea","last_reissued_at":"2026-06-04T01:09:25.880581Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:25.880581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"(2) Ant Group, (3) Hefei University of Technology), Changtao Miao (2), Xiaojing Chen (1), Xinyu Lu (1), Yunfeng Diao (3) ((1) Anhui University","submitted_at":"2026-06-03T10:35:47Z","abstract_excerpt":"AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models. In this paper, we explore reconstruction error as a discriminative forensic cue for AI-generated video detection. By reconstructing input videos with a pretrained WF-VAE, we observe that real and generated videos exhibit distinguishabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04706","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/2606.04706/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":"2606.04706","created_at":"2026-06-04T01:09:25.880703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04706v1","created_at":"2026-06-04T01:09:25.880703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04706","created_at":"2026-06-04T01:09:25.880703+00:00"},{"alias_kind":"pith_short_12","alias_value":"7D52HLKES66L","created_at":"2026-06-04T01:09:25.880703+00:00"},{"alias_kind":"pith_short_16","alias_value":"7D52HLKES66LVOPU","created_at":"2026-06-04T01:09:25.880703+00:00"},{"alias_kind":"pith_short_8","alias_value":"7D52HLKE","created_at":"2026-06-04T01:09:25.880703+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/7D52HLKES66LVOPUBXK2BJO3SU","json":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU.json","graph_json":"https://pith.science/api/pith-number/7D52HLKES66LVOPUBXK2BJO3SU/graph.json","events_json":"https://pith.science/api/pith-number/7D52HLKES66LVOPUBXK2BJO3SU/events.json","paper":"https://pith.science/paper/7D52HLKE"},"agent_actions":{"view_html":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU","download_json":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU.json","view_paper":"https://pith.science/paper/7D52HLKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04706&json=true","fetch_graph":"https://pith.science/api/pith-number/7D52HLKES66LVOPUBXK2BJO3SU/graph.json","fetch_events":"https://pith.science/api/pith-number/7D52HLKES66LVOPUBXK2BJO3SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU/action/storage_attestation","attest_author":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU/action/author_attestation","sign_citation":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU/action/citation_signature","submit_replication":"https://pith.science/pith/7D52HLKES66LVOPUBXK2BJO3SU/action/replication_record"}},"created_at":"2026-06-04T01:09:25.880703+00:00","updated_at":"2026-06-04T01:09:25.880703+00:00"}