{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I3MSDDRGIWRBTJFIJPEMTWTBLG","short_pith_number":"pith:I3MSDDRG","schema_version":"1.0","canonical_sha256":"46d9218e2645a219a4a84bc8c9da615981f3e988bda38c6f07d2242e1db6a8e9","source":{"kind":"arxiv","id":"2510.08398","version":4},"attestation_state":"computed","paper":{"title":"VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bairui Li, Hongyang Wei, Jinrui Zhang, Keze Wang, Lei Zhang, Xinyu Wei, Zeqing Wang, Zhen Guo","submitted_at":"2025-10-09T16:18:20Z","abstract_excerpt":"The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality-an essential property that differentiates videos from other modalities-remains largely unexplored. Third, existing benchmarks lack a systematic assessment of w"},"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":"2510.08398","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-09T16:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"1105a171bbf1b6e01deaa06dae137ea3fb176472dbc075fe9d9aa1e42b84c750","abstract_canon_sha256":"a2834609b8bc1c19f17bdae101ff4db1a970f3d4b8673b820621910a20188cd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:25.860619Z","signature_b64":"lLhoyjmJ2sFXhLuUrM0lkApYYDGHEqjC1lpc+pkupPm+UNKBHEFLUFxdf1CAg+ubwEcEK9/J0rKOWBgTPtfYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d9218e2645a219a4a84bc8c9da615981f3e988bda38c6f07d2242e1db6a8e9","last_reissued_at":"2026-05-20T00:00:25.859804Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:25.859804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bairui Li, Hongyang Wei, Jinrui Zhang, Keze Wang, Lei Zhang, Xinyu Wei, Zeqing Wang, Zhen Guo","submitted_at":"2025-10-09T16:18:20Z","abstract_excerpt":"The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality-an essential property that differentiates videos from other modalities-remains largely unexplored. Third, existing benchmarks lack a systematic assessment of w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08398","kind":"arxiv","version":4},"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/2510.08398/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":"2510.08398","created_at":"2026-05-20T00:00:25.859932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08398v4","created_at":"2026-05-20T00:00:25.859932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08398","created_at":"2026-05-20T00:00:25.859932+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3MSDDRGIWRB","created_at":"2026-05-20T00:00:25.859932+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3MSDDRGIWRBTJFI","created_at":"2026-05-20T00:00:25.859932+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3MSDDRG","created_at":"2026-05-20T00:00:25.859932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2512.01843","citing_title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07348","citing_title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10434","citing_title":"WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09591","citing_title":"From Pixels to Concepts: Do Segmentation Models Understand What They Segment?","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG","json":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG.json","graph_json":"https://pith.science/api/pith-number/I3MSDDRGIWRBTJFIJPEMTWTBLG/graph.json","events_json":"https://pith.science/api/pith-number/I3MSDDRGIWRBTJFIJPEMTWTBLG/events.json","paper":"https://pith.science/paper/I3MSDDRG"},"agent_actions":{"view_html":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG","download_json":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG.json","view_paper":"https://pith.science/paper/I3MSDDRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08398&json=true","fetch_graph":"https://pith.science/api/pith-number/I3MSDDRGIWRBTJFIJPEMTWTBLG/graph.json","fetch_events":"https://pith.science/api/pith-number/I3MSDDRGIWRBTJFIJPEMTWTBLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG/action/storage_attestation","attest_author":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG/action/author_attestation","sign_citation":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG/action/citation_signature","submit_replication":"https://pith.science/pith/I3MSDDRGIWRBTJFIJPEMTWTBLG/action/replication_record"}},"created_at":"2026-05-20T00:00:25.859932+00:00","updated_at":"2026-05-20T00:00:25.859932+00:00"}