{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2ZSKWGEHGVVZRTAMKQGLYBG2UR","short_pith_number":"pith:2ZSKWGEH","schema_version":"1.0","canonical_sha256":"d664ab1887356b98cc0c540cbc04daa45d8839adf72990e586705fd4749caa89","source":{"kind":"arxiv","id":"2011.01968","version":2},"attestation_state":"computed","paper":{"title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Shuran Song, Zhanpeng He, Zhenjia Xu","submitted_at":"2020-11-03T19:23:06Z","abstract_excerpt":"3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial observations are available; spatiotemporal continuity -- the movement of each object is continuous over space and time. In this paper, we introduce 3D Dynamic Scene Representation (DSR), a 3D volumetric scene representation that simultaneously discovers, tracks, reconstructs objects, and predicts their dynamics while capturing all three properties. We further prop"},"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":"2011.01968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-03T19:23:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b9d221764d9fd675a5c54b63121078a70198359f7d50425488103a16fba8d99b","abstract_canon_sha256":"4a38bcee61d1821bf106c11ba81df8abb67a3662ff2ba02592280d32ce8189e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:32.265373Z","signature_b64":"JaR5S9XyVeX5Gb7f9SCyJiWPYtDJT6uY/Z8NIym/y724gWezUoC7pMDbRgEmvFP+QByPk/3GKCrC7Ov4dRCgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d664ab1887356b98cc0c540cbc04daa45d8839adf72990e586705fd4749caa89","last_reissued_at":"2026-07-05T01:58:32.264937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:32.264937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Shuran Song, Zhanpeng He, Zhenjia Xu","submitted_at":"2020-11-03T19:23:06Z","abstract_excerpt":"3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial observations are available; spatiotemporal continuity -- the movement of each object is continuous over space and time. In this paper, we introduce 3D Dynamic Scene Representation (DSR), a 3D volumetric scene representation that simultaneously discovers, tracks, reconstructs objects, and predicts their dynamics while capturing all three properties. We further prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01968","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/2011.01968/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":"2011.01968","created_at":"2026-07-05T01:58:32.264994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01968v2","created_at":"2026-07-05T01:58:32.264994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01968","created_at":"2026-07-05T01:58:32.264994+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZSKWGEHGVVZ","created_at":"2026-07-05T01:58:32.264994+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZSKWGEHGVVZRTAM","created_at":"2026-07-05T01:58:32.264994+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZSKWGEH","created_at":"2026-07-05T01:58:32.264994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.19102","citing_title":"FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR","json":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR.json","graph_json":"https://pith.science/api/pith-number/2ZSKWGEHGVVZRTAMKQGLYBG2UR/graph.json","events_json":"https://pith.science/api/pith-number/2ZSKWGEHGVVZRTAMKQGLYBG2UR/events.json","paper":"https://pith.science/paper/2ZSKWGEH"},"agent_actions":{"view_html":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR","download_json":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR.json","view_paper":"https://pith.science/paper/2ZSKWGEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01968&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZSKWGEHGVVZRTAMKQGLYBG2UR/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZSKWGEHGVVZRTAMKQGLYBG2UR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR/action/storage_attestation","attest_author":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR/action/author_attestation","sign_citation":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR/action/citation_signature","submit_replication":"https://pith.science/pith/2ZSKWGEHGVVZRTAMKQGLYBG2UR/action/replication_record"}},"created_at":"2026-07-05T01:58:32.264994+00:00","updated_at":"2026-07-05T01:58:32.264994+00:00"}