{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RT2G4FGQ7Q6UPS7GTAWWX5ODAF","short_pith_number":"pith:RT2G4FGQ","schema_version":"1.0","canonical_sha256":"8cf46e14d0fc3d47cbe6982d6bf5c3014aa7a55f838a1d91cca5c829e4a6da1e","source":{"kind":"arxiv","id":"2603.26599","version":2},"attestation_state":"computed","paper":{"title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Karan Ahuja, Mar Gonzalez-Franco, Marta Tintore Gazulla, Orest Kupyn, Serge Belongie, Th\\'eo Uscidda, Zhaochong An","submitted_at":"2026-03-27T16:57:51Z","abstract_excerpt":"Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To prese"},"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":"2603.26599","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-27T16:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"185669096a40fba66d45fa642be17a217c1f1a4ba1888941dd8a07420ad48326","abstract_canon_sha256":"53d03ccf970ded297dc0f12f169f4b23d77167b8c86af25985a6f6fdce4d1b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:57.683613Z","signature_b64":"YVCgATDwk99w5zUgyGCHY14PBb05xGTFzZfzjR6+xHt8+xDMF2ok8B+tnBQX98vfruLXhjD9pH2TXaioP+WCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf46e14d0fc3d47cbe6982d6bf5c3014aa7a55f838a1d91cca5c829e4a6da1e","last_reissued_at":"2026-07-14T01:20:57.682705Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:57.682705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Karan Ahuja, Mar Gonzalez-Franco, Marta Tintore Gazulla, Orest Kupyn, Serge Belongie, Th\\'eo Uscidda, Zhaochong An","submitted_at":"2026-03-27T16:57:51Z","abstract_excerpt":"Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26599","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/2603.26599/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":"2603.26599","created_at":"2026-07-14T01:20:57.683134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26599v2","created_at":"2026-07-14T01:20:57.683134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26599","created_at":"2026-07-14T01:20:57.683134+00:00"},{"alias_kind":"pith_short_12","alias_value":"RT2G4FGQ7Q6U","created_at":"2026-07-14T01:20:57.683134+00:00"},{"alias_kind":"pith_short_16","alias_value":"RT2G4FGQ7Q6UPS7G","created_at":"2026-07-14T01:20:57.683134+00:00"},{"alias_kind":"pith_short_8","alias_value":"RT2G4FGQ","created_at":"2026-07-14T01:20:57.683134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2606.24876","citing_title":"FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02436","citing_title":"Geometry-Aware Implicit Memory for Video World Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25874","citing_title":"WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24763","citing_title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15458","citing_title":"Video Models Can Reason with Verifiable Rewards","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14269","citing_title":"PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24763","citing_title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF","json":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF.json","graph_json":"https://pith.science/api/pith-number/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/graph.json","events_json":"https://pith.science/api/pith-number/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/events.json","paper":"https://pith.science/paper/RT2G4FGQ"},"agent_actions":{"view_html":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF","download_json":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF.json","view_paper":"https://pith.science/paper/RT2G4FGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26599&json=true","fetch_graph":"https://pith.science/api/pith-number/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/graph.json","fetch_events":"https://pith.science/api/pith-number/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/action/storage_attestation","attest_author":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/action/author_attestation","sign_citation":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/action/citation_signature","submit_replication":"https://pith.science/pith/RT2G4FGQ7Q6UPS7GTAWWX5ODAF/action/replication_record"}},"created_at":"2026-07-14T01:20:57.683134+00:00","updated_at":"2026-07-14T01:20:57.683134+00:00"}