{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5RUDAJNAUSYMLJXHDVBHRQQWUC","short_pith_number":"pith:5RUDAJNA","schema_version":"1.0","canonical_sha256":"ec683025a0a4b0c5a6e71d4278c216a0972e4abff6b102f3b7ffb4a9a7cc212c","source":{"kind":"arxiv","id":"2311.02077","version":1},"attestation_state":"computed","paper":{"title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Boyi Li, Danfei Xu, Jiawei Yang, Marco Pavone, Or Litany, Sanja Fidler, Seung Wook Kim, Tong Che, Xinshuo Weng, Yue Wang","submitted_at":"2023-11-03T17:59:55Z","abstract_excerpt":"We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further ag"},"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":"2311.02077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-03T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"b6934525a5b5a499b61eddd5571a3ae151c0536a36f8a1dfb903fb43c70119aa","abstract_canon_sha256":"03f9c0787c589e099955429366c0c5e5147d466e60b40465250a560f33f4b75d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:49.933040Z","signature_b64":"aBQLMBVl7rf4fhzBr65uf+IQhpqwteu3TiybiiyhWpHfOgSJxjQXgeoCRs5VQgsWKZnuaz0XS3OZOUrT2iQrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec683025a0a4b0c5a6e71d4278c216a0972e4abff6b102f3b7ffb4a9a7cc212c","last_reissued_at":"2026-07-05T07:08:49.932569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:49.932569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Boyi Li, Danfei Xu, Jiawei Yang, Marco Pavone, Or Litany, Sanja Fidler, Seung Wook Kim, Tong Che, Xinshuo Weng, Yue Wang","submitted_at":"2023-11-03T17:59:55Z","abstract_excerpt":"We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02077","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/2311.02077/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":"2311.02077","created_at":"2026-07-05T07:08:49.932623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02077v1","created_at":"2026-07-05T07:08:49.932623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02077","created_at":"2026-07-05T07:08:49.932623+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RUDAJNAUSYM","created_at":"2026-07-05T07:08:49.932623+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RUDAJNAUSYMLJXH","created_at":"2026-07-05T07:08:49.932623+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RUDAJNA","created_at":"2026-07-05T07:08:49.932623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03909","citing_title":"SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29374","citing_title":"L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26113","citing_title":"AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00746","citing_title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23180","citing_title":"GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03210","citing_title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23262","citing_title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11594","citing_title":"PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07910","citing_title":"One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07910","citing_title":"One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04435","citing_title":"Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC","json":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC.json","graph_json":"https://pith.science/api/pith-number/5RUDAJNAUSYMLJXHDVBHRQQWUC/graph.json","events_json":"https://pith.science/api/pith-number/5RUDAJNAUSYMLJXHDVBHRQQWUC/events.json","paper":"https://pith.science/paper/5RUDAJNA"},"agent_actions":{"view_html":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC","download_json":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC.json","view_paper":"https://pith.science/paper/5RUDAJNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02077&json=true","fetch_graph":"https://pith.science/api/pith-number/5RUDAJNAUSYMLJXHDVBHRQQWUC/graph.json","fetch_events":"https://pith.science/api/pith-number/5RUDAJNAUSYMLJXHDVBHRQQWUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC/action/storage_attestation","attest_author":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC/action/author_attestation","sign_citation":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC/action/citation_signature","submit_replication":"https://pith.science/pith/5RUDAJNAUSYMLJXHDVBHRQQWUC/action/replication_record"}},"created_at":"2026-07-05T07:08:49.932623+00:00","updated_at":"2026-07-05T07:08:49.932623+00:00"}