{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JULBQKK3ISO5KPMGBSDFQGGMRC","short_pith_number":"pith:JULBQKK3","schema_version":"1.0","canonical_sha256":"4d1618295b449dd53d860c865818cc88ab9d006c20f83aacb6f7bf0e9f6591cb","source":{"kind":"arxiv","id":"2401.18075","version":2},"attestation_state":"computed","paper":{"title":"CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charles Packer, Harshil Bhatia, Jiezhi Yang, Joseph Gonzalez, Khushi Desai, Nicholas Rhinehart, Rowan McAllister","submitted_at":"2024-01-31T18:56:09Z","abstract_excerpt":"We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes through time. Our latents condition a global Neural Radiance Field (NeRF) to represent a 3D scene model, enabling explainable predictions and straightforward downstream planning. This approach models the world as a POMDP and considers complex scenarios of uncertainty in environmental states and dynamics. Specifically, we employ a two-stage training of Pose-Condi"},"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":"2401.18075","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T18:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"35750987550b0463dd641d3d8df87ccf4e9a0d2ce08100166c72cf126850f150","abstract_canon_sha256":"83c8cef1c455525b70e5abaf27d08439ceac73f034c6acdda1231c23ccb48c12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:21.046109Z","signature_b64":"61lf8PiEn0wyecQZ9mYIe0+v2PiQ/XVcOAr7nJo/Lt+FIBL3KtvYpeCSIc/XxKbu/uv07iKMrrmVFLpC3MtrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1618295b449dd53d860c865818cc88ab9d006c20f83aacb6f7bf0e9f6591cb","last_reissued_at":"2026-07-05T08:46:21.045452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:21.045452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charles Packer, Harshil Bhatia, Jiezhi Yang, Joseph Gonzalez, Khushi Desai, Nicholas Rhinehart, Rowan McAllister","submitted_at":"2024-01-31T18:56:09Z","abstract_excerpt":"We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes through time. Our latents condition a global Neural Radiance Field (NeRF) to represent a 3D scene model, enabling explainable predictions and straightforward downstream planning. This approach models the world as a POMDP and considers complex scenarios of uncertainty in environmental states and dynamics. Specifically, we employ a two-stage training of Pose-Condi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.18075","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/2401.18075/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":"2401.18075","created_at":"2026-07-05T08:46:21.045531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.18075v2","created_at":"2026-07-05T08:46:21.045531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18075","created_at":"2026-07-05T08:46:21.045531+00:00"},{"alias_kind":"pith_short_12","alias_value":"JULBQKK3ISO5","created_at":"2026-07-05T08:46:21.045531+00:00"},{"alias_kind":"pith_short_16","alias_value":"JULBQKK3ISO5KPMG","created_at":"2026-07-05T08:46:21.045531+00:00"},{"alias_kind":"pith_short_8","alias_value":"JULBQKK3","created_at":"2026-07-05T08:46:21.045531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13569","citing_title":"Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC","json":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC.json","graph_json":"https://pith.science/api/pith-number/JULBQKK3ISO5KPMGBSDFQGGMRC/graph.json","events_json":"https://pith.science/api/pith-number/JULBQKK3ISO5KPMGBSDFQGGMRC/events.json","paper":"https://pith.science/paper/JULBQKK3"},"agent_actions":{"view_html":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC","download_json":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC.json","view_paper":"https://pith.science/paper/JULBQKK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.18075&json=true","fetch_graph":"https://pith.science/api/pith-number/JULBQKK3ISO5KPMGBSDFQGGMRC/graph.json","fetch_events":"https://pith.science/api/pith-number/JULBQKK3ISO5KPMGBSDFQGGMRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC/action/storage_attestation","attest_author":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC/action/author_attestation","sign_citation":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC/action/citation_signature","submit_replication":"https://pith.science/pith/JULBQKK3ISO5KPMGBSDFQGGMRC/action/replication_record"}},"created_at":"2026-07-05T08:46:21.045531+00:00","updated_at":"2026-07-05T08:46:21.045531+00:00"}