{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MNDTZI5HLV4O6T2YVEGCMBEQBU","short_pith_number":"pith:MNDTZI5H","schema_version":"1.0","canonical_sha256":"63473ca3a75d78ef4f58a90c2604900d383ff491863a336a2b1e9c4a7d45abff","source":{"kind":"arxiv","id":"2510.21615","version":2},"attestation_state":"computed","paper":{"title":"Epipolar Geometry Improves Video Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Rupprecht, Fabian Manhardt, Federico Tombari, Marta Tintore Gazulla, Orest Kupyn, Th\\'eo Uscidda","submitted_at":"2025-10-24T16:21:37Z","abstract_excerpt":"Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. 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":"2510.21615","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T16:21:37Z","cross_cats_sorted":[],"title_canon_sha256":"091299af78b6ef67c310027d271c4c00d7247b5be7e083d68135706200f28062","abstract_canon_sha256":"83a2e7f3389605efd2993d8e3a38442f2baf772c7d067b04b587b3bc60bf2f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:04.497868Z","signature_b64":"ot44PKC1jBlOT67tgWtihnDysfgPMSuaiVG5wHsTFtwwqzPU8bm2UjHGNp8Ity9QS/CsZar4AF9bOYdf0FzVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63473ca3a75d78ef4f58a90c2604900d383ff491863a336a2b1e9c4a7d45abff","last_reissued_at":"2026-06-19T16:12:04.497450Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:04.497450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epipolar Geometry Improves Video Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Rupprecht, Fabian Manhardt, Federico Tombari, Marta Tintore Gazulla, Orest Kupyn, Th\\'eo Uscidda","submitted_at":"2025-10-24T16:21:37Z","abstract_excerpt":"Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21615","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/2510.21615/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":"2510.21615","created_at":"2026-06-19T16:12:04.497509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.21615v2","created_at":"2026-06-19T16:12:04.497509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21615","created_at":"2026-06-19T16:12:04.497509+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNDTZI5HLV4O","created_at":"2026-06-19T16:12:04.497509+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNDTZI5HLV4O6T2Y","created_at":"2026-06-19T16:12:04.497509+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNDTZI5H","created_at":"2026-06-19T16:12:04.497509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19949","citing_title":"Feed-Forward Gaussian Splatting from Sparse Aerial Views","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2601.23286","citing_title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU","json":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU.json","graph_json":"https://pith.science/api/pith-number/MNDTZI5HLV4O6T2YVEGCMBEQBU/graph.json","events_json":"https://pith.science/api/pith-number/MNDTZI5HLV4O6T2YVEGCMBEQBU/events.json","paper":"https://pith.science/paper/MNDTZI5H"},"agent_actions":{"view_html":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU","download_json":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU.json","view_paper":"https://pith.science/paper/MNDTZI5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.21615&json=true","fetch_graph":"https://pith.science/api/pith-number/MNDTZI5HLV4O6T2YVEGCMBEQBU/graph.json","fetch_events":"https://pith.science/api/pith-number/MNDTZI5HLV4O6T2YVEGCMBEQBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU/action/storage_attestation","attest_author":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU/action/author_attestation","sign_citation":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU/action/citation_signature","submit_replication":"https://pith.science/pith/MNDTZI5HLV4O6T2YVEGCMBEQBU/action/replication_record"}},"created_at":"2026-06-19T16:12:04.497509+00:00","updated_at":"2026-06-19T16:12:04.497509+00:00"}