{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BLVGORU7G3UEUOVHRMDY7BXAH5","short_pith_number":"pith:BLVGORU7","schema_version":"1.0","canonical_sha256":"0aea67469f36e84a3aa78b078f86e03f6f60bac7d70f80571310ebc871fbe793","source":{"kind":"arxiv","id":"2606.24829","version":1},"attestation_state":"computed","paper":{"title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenrui Fan, Paolo Favaro","submitted_at":"2026-06-23T17:12:21Z","abstract_excerpt":"Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs, visual plausibility is insufficient: the generated frames should also provide coherent multi-view evidence for a single static 3D scene. We introduce GeoT2V-Bench, a reconstruction-based diagnostic benchmark for evaluating whether camera-prompted T2V clips can support explicit rigid 3D reconstruction. Our pipeline estimates per-frame camera intrinsics and poses with VGGT-style geometry estimation, fits DeformableGS,"},"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":"2606.24829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T17:12:21Z","cross_cats_sorted":[],"title_canon_sha256":"0db6b2f62780946414e71bae7028248b1cd4f7a596ddbd4082167b55657ff235","abstract_canon_sha256":"b9b38ae2ce194a392d3061136553cbf20c97d6066ee07b3ced561e27a2ffa14e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:43.418909Z","signature_b64":"iu+lVGQPln0imbVh2z/4wR+Qonf2AzhSPvWg9yUZWhaU/2j9MlNK6Xnxp+mGMdzG+FK7JJWhDfSf7seZOrCLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aea67469f36e84a3aa78b078f86e03f6f60bac7d70f80571310ebc871fbe793","last_reissued_at":"2026-06-24T01:15:43.418539Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:43.418539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenrui Fan, Paolo Favaro","submitted_at":"2026-06-23T17:12:21Z","abstract_excerpt":"Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs, visual plausibility is insufficient: the generated frames should also provide coherent multi-view evidence for a single static 3D scene. We introduce GeoT2V-Bench, a reconstruction-based diagnostic benchmark for evaluating whether camera-prompted T2V clips can support explicit rigid 3D reconstruction. Our pipeline estimates per-frame camera intrinsics and poses with VGGT-style geometry estimation, fits DeformableGS,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24829","kind":"arxiv","version":1},"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/2606.24829/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":"2606.24829","created_at":"2026-06-24T01:15:43.418598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24829v1","created_at":"2026-06-24T01:15:43.418598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24829","created_at":"2026-06-24T01:15:43.418598+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLVGORU7G3UE","created_at":"2026-06-24T01:15:43.418598+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLVGORU7G3UEUOVH","created_at":"2026-06-24T01:15:43.418598+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLVGORU7","created_at":"2026-06-24T01:15:43.418598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5","json":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5.json","graph_json":"https://pith.science/api/pith-number/BLVGORU7G3UEUOVHRMDY7BXAH5/graph.json","events_json":"https://pith.science/api/pith-number/BLVGORU7G3UEUOVHRMDY7BXAH5/events.json","paper":"https://pith.science/paper/BLVGORU7"},"agent_actions":{"view_html":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5","download_json":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5.json","view_paper":"https://pith.science/paper/BLVGORU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24829&json=true","fetch_graph":"https://pith.science/api/pith-number/BLVGORU7G3UEUOVHRMDY7BXAH5/graph.json","fetch_events":"https://pith.science/api/pith-number/BLVGORU7G3UEUOVHRMDY7BXAH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5/action/storage_attestation","attest_author":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5/action/author_attestation","sign_citation":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5/action/citation_signature","submit_replication":"https://pith.science/pith/BLVGORU7G3UEUOVHRMDY7BXAH5/action/replication_record"}},"created_at":"2026-06-24T01:15:43.418598+00:00","updated_at":"2026-06-24T01:15:43.418598+00:00"}