{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QQRSBY2MZ73BUFAR35EKVCPRBM","short_pith_number":"pith:QQRSBY2M","schema_version":"1.0","canonical_sha256":"842320e34ccff61a1411df48aa89f10b0774e09fccfa895512e1dc38c6b59de8","source":{"kind":"arxiv","id":"2411.13609","version":2},"attestation_state":"computed","paper":{"title":"What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Song, Lingyan Hao, Songlin Li, Xinyu Hu, Zihan Wang","submitted_at":"2024-11-20T01:40:00Z","abstract_excerpt":"As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fr\\'echet Video Distance (FVD), Inception Score (IS), and ClipSim, measure quality primarily in latent space rather than from a human visual perspective, often overlooking key aspects like appearance and motion consistency to physical laws. In this paper, we propose a novel metric, VAMP (Visual Appearance and Motion Plausibility), that evaluates both the visual appearance and physical plausibility of generated videos. VAMP is composed of two main com"},"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":"2411.13609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T01:40:00Z","cross_cats_sorted":[],"title_canon_sha256":"034b3df1e7c56cd5a7ae50dc37e0f7bffc86376449ac744be0d5f601686399af","abstract_canon_sha256":"ee2bb0cc4455562d7da74df94c3cabddfdf5b690ad0c8e578576adfa9d62f9eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:21.519173Z","signature_b64":"+1rwH3sqdJsvkEj6tlX5mdGDsJ3g5kzKkc3PN983Z7Od5Rq9EK2+6IFJq2q6pdwBUfnCWB/gHMHokDZAU85HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"842320e34ccff61a1411df48aa89f10b0774e09fccfa895512e1dc38c6b59de8","last_reissued_at":"2026-07-05T09:40:21.518706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:21.518706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Song, Lingyan Hao, Songlin Li, Xinyu Hu, Zihan Wang","submitted_at":"2024-11-20T01:40:00Z","abstract_excerpt":"As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fr\\'echet Video Distance (FVD), Inception Score (IS), and ClipSim, measure quality primarily in latent space rather than from a human visual perspective, often overlooking key aspects like appearance and motion consistency to physical laws. In this paper, we propose a novel metric, VAMP (Visual Appearance and Motion Plausibility), that evaluates both the visual appearance and physical plausibility of generated videos. VAMP is composed of two main com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13609","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/2411.13609/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":"2411.13609","created_at":"2026-07-05T09:40:21.518763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13609v2","created_at":"2026-07-05T09:40:21.518763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13609","created_at":"2026-07-05T09:40:21.518763+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQRSBY2MZ73B","created_at":"2026-07-05T09:40:21.518763+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQRSBY2MZ73BUFAR","created_at":"2026-07-05T09:40:21.518763+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQRSBY2M","created_at":"2026-07-05T09:40:21.518763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18943","citing_title":"Physics-IQ Verified","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27705","citing_title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30339","citing_title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07230","citing_title":"PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM","json":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM.json","graph_json":"https://pith.science/api/pith-number/QQRSBY2MZ73BUFAR35EKVCPRBM/graph.json","events_json":"https://pith.science/api/pith-number/QQRSBY2MZ73BUFAR35EKVCPRBM/events.json","paper":"https://pith.science/paper/QQRSBY2M"},"agent_actions":{"view_html":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM","download_json":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM.json","view_paper":"https://pith.science/paper/QQRSBY2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13609&json=true","fetch_graph":"https://pith.science/api/pith-number/QQRSBY2MZ73BUFAR35EKVCPRBM/graph.json","fetch_events":"https://pith.science/api/pith-number/QQRSBY2MZ73BUFAR35EKVCPRBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM/action/storage_attestation","attest_author":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM/action/author_attestation","sign_citation":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM/action/citation_signature","submit_replication":"https://pith.science/pith/QQRSBY2MZ73BUFAR35EKVCPRBM/action/replication_record"}},"created_at":"2026-07-05T09:40:21.518763+00:00","updated_at":"2026-07-05T09:40:21.518763+00:00"}