{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QGAIAFFPPOKRJSP2K7UNMQLMMR","short_pith_number":"pith:QGAIAFFP","schema_version":"1.0","canonical_sha256":"81808014af7b9514c9fa57e8d6416c647ddf1e5b6c6e0f504fe1843df797125a","source":{"kind":"arxiv","id":"2503.23452","version":2},"attestation_state":"computed","paper":{"title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Feilin Han, Hongxiang Li, Ke Fan, Shangkun Sun, Wei Liu, Wei Zhai, Yang Cao, Yuhang Yang, Zheng-Jun Zha","submitted_at":"2025-03-30T14:12:21Z","abstract_excerpt":"The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators struggling with Out-of-Distribution (OOD) cases, and misalignment between computed metrics and human preferences. To bridge the gap, we propose VideoGen-Eval, an agent evaluation system that integrates LLM-based content structuring, MLLM-based content judgment, and patch tools designed for temporal-dense dimensions, to achieve a dynamic, flexible, and expanda"},"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":"2503.23452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T14:12:21Z","cross_cats_sorted":[],"title_canon_sha256":"a3c45918d3e8b851552af41d99d68311f37368946596b151ccf1ab9678106d96","abstract_canon_sha256":"8259f4ebb2d226b280d4ade9425d31d72f116637b5786d030be6601c88c4d2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:45.577550Z","signature_b64":"bos2eNvxb72IGkJ5RUvmowUBk+rGZ1T5Oi3vd6NSoLFkIE7uLeclOyfEDxrxzhaqSNwS6+oSMyfzDJwK8IT3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81808014af7b9514c9fa57e8d6416c647ddf1e5b6c6e0f504fe1843df797125a","last_reissued_at":"2026-07-05T10:54:45.576974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:45.576974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Feilin Han, Hongxiang Li, Ke Fan, Shangkun Sun, Wei Liu, Wei Zhai, Yang Cao, Yuhang Yang, Zheng-Jun Zha","submitted_at":"2025-03-30T14:12:21Z","abstract_excerpt":"The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators struggling with Out-of-Distribution (OOD) cases, and misalignment between computed metrics and human preferences. To bridge the gap, we propose VideoGen-Eval, an agent evaluation system that integrates LLM-based content structuring, MLLM-based content judgment, and patch tools designed for temporal-dense dimensions, to achieve a dynamic, flexible, and expanda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23452","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/2503.23452/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":"2503.23452","created_at":"2026-07-05T10:54:45.577041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23452v2","created_at":"2026-07-05T10:54:45.577041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23452","created_at":"2026-07-05T10:54:45.577041+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGAIAFFPPOKR","created_at":"2026-07-05T10:54:45.577041+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGAIAFFPPOKRJSP2","created_at":"2026-07-05T10:54:45.577041+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGAIAFFP","created_at":"2026-07-05T10:54:45.577041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28531","citing_title":"A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28385","citing_title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07823","citing_title":"LPM 1.0: Video-based Character Performance Model","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":168,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR","json":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR.json","graph_json":"https://pith.science/api/pith-number/QGAIAFFPPOKRJSP2K7UNMQLMMR/graph.json","events_json":"https://pith.science/api/pith-number/QGAIAFFPPOKRJSP2K7UNMQLMMR/events.json","paper":"https://pith.science/paper/QGAIAFFP"},"agent_actions":{"view_html":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR","download_json":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR.json","view_paper":"https://pith.science/paper/QGAIAFFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23452&json=true","fetch_graph":"https://pith.science/api/pith-number/QGAIAFFPPOKRJSP2K7UNMQLMMR/graph.json","fetch_events":"https://pith.science/api/pith-number/QGAIAFFPPOKRJSP2K7UNMQLMMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR/action/storage_attestation","attest_author":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR/action/author_attestation","sign_citation":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR/action/citation_signature","submit_replication":"https://pith.science/pith/QGAIAFFPPOKRJSP2K7UNMQLMMR/action/replication_record"}},"created_at":"2026-07-05T10:54:45.577041+00:00","updated_at":"2026-07-05T10:54:45.577041+00:00"}