{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJLBLLOD5FWBSA4EEIPWDJDJSM","short_pith_number":"pith:ZJLBLLOD","schema_version":"1.0","canonical_sha256":"ca5615adc3e96c190384221f61a4699337a6b720c12a6dbb3158e8ce73057336","source":{"kind":"arxiv","id":"2302.01133","version":2},"attestation_state":"computed","paper":{"title":"SceneScape: Text-Driven Consistent Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Abecasis, Rafail Fridman, Tali Dekel, Yoni Kasten","submitted_at":"2023-02-02T14:47:19Z","abstract_excerpt":"We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses. We introduce a novel framework that generates such videos in an online fashion by combining the generative power of a pre-trained text-to-image model with the geometric priors learned by a pre-trained monocular depth prediction model. To tackle the pivotal challenge of achieving 3D consistency, i.e., synthesizing videos that depict geometrically-plausible scenes, we deploy an online test-time training to encou"},"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":"2302.01133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-02T14:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"ea444f7d18e0740b19d23fee2aeb0f1578b6c8ce3825b1f4984e265687e14a8e","abstract_canon_sha256":"348c6431122bf0bc76d388645cf528cd27ebc9aa31614621363261960d9680e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:23.262451Z","signature_b64":"6l8E8XCC9kzWT1jTWxDvjPKLGLzR63uWm0WsmWce7bF6nnHIk+bc7OPM74nzNm8YtAOCdsqYF7xhOp0cqemLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5615adc3e96c190384221f61a4699337a6b720c12a6dbb3158e8ce73057336","last_reissued_at":"2026-07-05T06:15:23.261901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:23.261901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SceneScape: Text-Driven Consistent Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Abecasis, Rafail Fridman, Tali Dekel, Yoni Kasten","submitted_at":"2023-02-02T14:47:19Z","abstract_excerpt":"We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses. We introduce a novel framework that generates such videos in an online fashion by combining the generative power of a pre-trained text-to-image model with the geometric priors learned by a pre-trained monocular depth prediction model. To tackle the pivotal challenge of achieving 3D consistency, i.e., synthesizing videos that depict geometrically-plausible scenes, we deploy an online test-time training to encou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01133","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/2302.01133/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":"2302.01133","created_at":"2026-07-05T06:15:23.261962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01133v2","created_at":"2026-07-05T06:15:23.261962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01133","created_at":"2026-07-05T06:15:23.261962+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJLBLLOD5FWB","created_at":"2026-07-05T06:15:23.261962+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJLBLLOD5FWBSA4E","created_at":"2026-07-05T06:15:23.261962+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJLBLLOD","created_at":"2026-07-05T06:15:23.261962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":238,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM","json":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM.json","graph_json":"https://pith.science/api/pith-number/ZJLBLLOD5FWBSA4EEIPWDJDJSM/graph.json","events_json":"https://pith.science/api/pith-number/ZJLBLLOD5FWBSA4EEIPWDJDJSM/events.json","paper":"https://pith.science/paper/ZJLBLLOD"},"agent_actions":{"view_html":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM","download_json":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM.json","view_paper":"https://pith.science/paper/ZJLBLLOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01133&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJLBLLOD5FWBSA4EEIPWDJDJSM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJLBLLOD5FWBSA4EEIPWDJDJSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM/action/storage_attestation","attest_author":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM/action/author_attestation","sign_citation":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM/action/citation_signature","submit_replication":"https://pith.science/pith/ZJLBLLOD5FWBSA4EEIPWDJDJSM/action/replication_record"}},"created_at":"2026-07-05T06:15:23.261962+00:00","updated_at":"2026-07-05T06:15:23.261962+00:00"}