{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RNVNVDNKS6AZJET3P6RXJJQBPK","short_pith_number":"pith:RNVNVDNK","schema_version":"1.0","canonical_sha256":"8b6ada8daa978194927b7fa374a6017aa7e47afe3a2f29eeacfc076f92a00a53","source":{"kind":"arxiv","id":"2409.03685","version":3},"attestation_state":"computed","paper":{"title":"View-Invariant Policy Learning via Zero-Shot Novel View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Blake Wulfe, Jiajun Wu, Katherine Liu, Kyle Sargent, Sergey Zakharov, Stephen Tian, Vitor Guizilini","submitted_at":"2024-09-05T16:39:21Z","abstract_excerpt":"Large-scale visuomotor policy learning is a promising approach toward developing generalizable manipulation systems. Yet, policies that can be deployed on diverse embodiments, environments, and observational modalities remain elusive. In this work, we investigate how knowledge from large-scale visual data of the world may be used to address one axis of variation for generalizable manipulation: observational viewpoint. Specifically, we study single-image novel view synthesis models, which learn 3D-aware scene-level priors by rendering images of the same scene from alternate camera viewpoints gi"},"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":"2409.03685","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-05T16:39:21Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"09f9e0b1382cc58c3c0d6d76f6a9f75002bec0ec81dd8829168b4e13806548ce","abstract_canon_sha256":"1e871b051932c0dac582c826e93c9d9812c46fe00940d9e0379bd45952150faa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:12.290261Z","signature_b64":"4c2K1puuuNQuElRYn0EDt436v37UNkhmc4ls9wU1Vjob5yFJIyolk4G9vNymq9zPqxfUOPRNn2M67Th6ekI2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6ada8daa978194927b7fa374a6017aa7e47afe3a2f29eeacfc076f92a00a53","last_reissued_at":"2026-07-05T11:13:12.289709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:12.289709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"View-Invariant Policy Learning via Zero-Shot Novel View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Blake Wulfe, Jiajun Wu, Katherine Liu, Kyle Sargent, Sergey Zakharov, Stephen Tian, Vitor Guizilini","submitted_at":"2024-09-05T16:39:21Z","abstract_excerpt":"Large-scale visuomotor policy learning is a promising approach toward developing generalizable manipulation systems. Yet, policies that can be deployed on diverse embodiments, environments, and observational modalities remain elusive. In this work, we investigate how knowledge from large-scale visual data of the world may be used to address one axis of variation for generalizable manipulation: observational viewpoint. Specifically, we study single-image novel view synthesis models, which learn 3D-aware scene-level priors by rendering images of the same scene from alternate camera viewpoints gi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03685","kind":"arxiv","version":3},"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/2409.03685/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":"2409.03685","created_at":"2026-07-05T11:13:12.289783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03685v3","created_at":"2026-07-05T11:13:12.289783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03685","created_at":"2026-07-05T11:13:12.289783+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNVNVDNKS6AZ","created_at":"2026-07-05T11:13:12.289783+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNVNVDNKS6AZJET3","created_at":"2026-07-05T11:13:12.289783+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNVNVDNK","created_at":"2026-07-05T11:13:12.289783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21501","citing_title":"UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19586","citing_title":"One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15023","citing_title":"DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK","json":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK.json","graph_json":"https://pith.science/api/pith-number/RNVNVDNKS6AZJET3P6RXJJQBPK/graph.json","events_json":"https://pith.science/api/pith-number/RNVNVDNKS6AZJET3P6RXJJQBPK/events.json","paper":"https://pith.science/paper/RNVNVDNK"},"agent_actions":{"view_html":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK","download_json":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK.json","view_paper":"https://pith.science/paper/RNVNVDNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03685&json=true","fetch_graph":"https://pith.science/api/pith-number/RNVNVDNKS6AZJET3P6RXJJQBPK/graph.json","fetch_events":"https://pith.science/api/pith-number/RNVNVDNKS6AZJET3P6RXJJQBPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK/action/storage_attestation","attest_author":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK/action/author_attestation","sign_citation":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK/action/citation_signature","submit_replication":"https://pith.science/pith/RNVNVDNKS6AZJET3P6RXJJQBPK/action/replication_record"}},"created_at":"2026-07-05T11:13:12.289783+00:00","updated_at":"2026-07-05T11:13:12.289783+00:00"}