{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TDPAKGOJMRXFWTTPB2B6U32MHX","short_pith_number":"pith:TDPAKGOJ","schema_version":"1.0","canonical_sha256":"98de0519c9646e5b4e6f0e83ea6f4c3dd922591d9b68e08eff1f6360c4bd31d3","source":{"kind":"arxiv","id":"2006.01031","version":4},"attestation_state":"computed","paper":{"title":"A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David M. Rosen, Jonathan Kelly, Matthew Giamou, Nicholas Roy, Valentin Peretroukhin, W. Nicholas Greene","submitted_at":"2020-06-01T15:57:45Z","abstract_excerpt":"Accurate rotation estimation is at the heart of robot perception tasks such as visual odometry and object pose estimation. Deep neural networks have provided a new way to perform these tasks, and the choice of rotation representation is an important part of network design. In this work, we present a novel symmetric matrix representation of the 3D rotation group, SO(3), with two important properties that make it particularly suitable for learned models: (1) it satisfies a smoothness property that improves convergence and generalization when regressing large rotation targets, and (2) it encodes "},"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":"2006.01031","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-01T15:57:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"627397268ec83a8fd178afc4305476fe5f90ffead0e1a9ca532ea070883262c1","abstract_canon_sha256":"2274ddb8d486549117960423d2f229f113bb6d73abda3b511f55085d6adc1ec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:28.526904Z","signature_b64":"3OroLMS0mTpXg9lvZgrp6cgWQ/cxXIOFHBV3KNXOKaaINEQ1s/wj5q5U0EvHw8CKqevgFIJG6VPBBJa8aChFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98de0519c9646e5b4e6f0e83ea6f4c3dd922591d9b68e08eff1f6360c4bd31d3","last_reissued_at":"2026-07-05T02:07:28.526480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:28.526480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David M. Rosen, Jonathan Kelly, Matthew Giamou, Nicholas Roy, Valentin Peretroukhin, W. Nicholas Greene","submitted_at":"2020-06-01T15:57:45Z","abstract_excerpt":"Accurate rotation estimation is at the heart of robot perception tasks such as visual odometry and object pose estimation. Deep neural networks have provided a new way to perform these tasks, and the choice of rotation representation is an important part of network design. In this work, we present a novel symmetric matrix representation of the 3D rotation group, SO(3), with two important properties that make it particularly suitable for learned models: (1) it satisfies a smoothness property that improves convergence and generalization when regressing large rotation targets, and (2) it encodes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01031","kind":"arxiv","version":4},"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/2006.01031/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":"2006.01031","created_at":"2026-07-05T02:07:28.526534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01031v4","created_at":"2026-07-05T02:07:28.526534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01031","created_at":"2026-07-05T02:07:28.526534+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDPAKGOJMRXF","created_at":"2026-07-05T02:07:28.526534+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDPAKGOJMRXFWTTP","created_at":"2026-07-05T02:07:28.526534+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDPAKGOJ","created_at":"2026-07-05T02:07:28.526534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00215","citing_title":"ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06479","citing_title":"Risk-Controlled Post-Processing of Decision Policies","ref_index":286,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX","json":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX.json","graph_json":"https://pith.science/api/pith-number/TDPAKGOJMRXFWTTPB2B6U32MHX/graph.json","events_json":"https://pith.science/api/pith-number/TDPAKGOJMRXFWTTPB2B6U32MHX/events.json","paper":"https://pith.science/paper/TDPAKGOJ"},"agent_actions":{"view_html":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX","download_json":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX.json","view_paper":"https://pith.science/paper/TDPAKGOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01031&json=true","fetch_graph":"https://pith.science/api/pith-number/TDPAKGOJMRXFWTTPB2B6U32MHX/graph.json","fetch_events":"https://pith.science/api/pith-number/TDPAKGOJMRXFWTTPB2B6U32MHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX/action/storage_attestation","attest_author":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX/action/author_attestation","sign_citation":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX/action/citation_signature","submit_replication":"https://pith.science/pith/TDPAKGOJMRXFWTTPB2B6U32MHX/action/replication_record"}},"created_at":"2026-07-05T02:07:28.526534+00:00","updated_at":"2026-07-05T02:07:28.526534+00:00"}