{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F3X3VFYPDQP4LGZKSACOO7PXYX","short_pith_number":"pith:F3X3VFYP","schema_version":"1.0","canonical_sha256":"2eefba970f1c1fc59b2a9004e77df7c5eb1cd21be869267048beae6de225680b","source":{"kind":"arxiv","id":"2412.10431","version":1},"attestation_state":"computed","paper":{"title":"CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Harry Zhang, Luca Carlone","submitted_at":"2024-12-11T03:11:44Z","abstract_excerpt":"We introduce CUPS, a novel method for learning sequence-to-sequence 3D human shapes and poses from RGB videos with uncertainty quantification. To improve on top of prior work, we develop a method to generate and score multiple hypotheses during training, effectively integrating uncertainty quantification into the learning process. This process results in a deep uncertainty function that is trained end-to-end with the 3D pose estimator. Post-training, the learned deep uncertainty model is used as the conformity score, which can be used to calibrate a conformal predictor in order to assess the q"},"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":"2412.10431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T03:11:44Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a3336d02c8d1b462a3ae549ee639fed399cdfb667d56bb14004f07278ff7a54c","abstract_canon_sha256":"5868784762963283040079e7afaadf07d47f7e621ef0708c0673b6d494ca484a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:15.838497Z","signature_b64":"79K96vu8YqHPrty0cdi+sK/kS0iXc15+JJ9GOhHrwrIc/64NKEHCiSkhN/5alZhO7pslb32Jij9Ucavh0R5TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eefba970f1c1fc59b2a9004e77df7c5eb1cd21be869267048beae6de225680b","last_reissued_at":"2026-07-05T09:49:15.838000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:15.838000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Harry Zhang, Luca Carlone","submitted_at":"2024-12-11T03:11:44Z","abstract_excerpt":"We introduce CUPS, a novel method for learning sequence-to-sequence 3D human shapes and poses from RGB videos with uncertainty quantification. To improve on top of prior work, we develop a method to generate and score multiple hypotheses during training, effectively integrating uncertainty quantification into the learning process. This process results in a deep uncertainty function that is trained end-to-end with the 3D pose estimator. Post-training, the learned deep uncertainty model is used as the conformity score, which can be used to calibrate a conformal predictor in order to assess the q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10431","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/2412.10431/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":"2412.10431","created_at":"2026-07-05T09:49:15.838058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10431v1","created_at":"2026-07-05T09:49:15.838058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10431","created_at":"2026-07-05T09:49:15.838058+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3X3VFYPDQP4","created_at":"2026-07-05T09:49:15.838058+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3X3VFYPDQP4LGZK","created_at":"2026-07-05T09:49:15.838058+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3X3VFYP","created_at":"2026-07-05T09:49:15.838058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX","json":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX.json","graph_json":"https://pith.science/api/pith-number/F3X3VFYPDQP4LGZKSACOO7PXYX/graph.json","events_json":"https://pith.science/api/pith-number/F3X3VFYPDQP4LGZKSACOO7PXYX/events.json","paper":"https://pith.science/paper/F3X3VFYP"},"agent_actions":{"view_html":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX","download_json":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX.json","view_paper":"https://pith.science/paper/F3X3VFYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10431&json=true","fetch_graph":"https://pith.science/api/pith-number/F3X3VFYPDQP4LGZKSACOO7PXYX/graph.json","fetch_events":"https://pith.science/api/pith-number/F3X3VFYPDQP4LGZKSACOO7PXYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX/action/storage_attestation","attest_author":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX/action/author_attestation","sign_citation":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX/action/citation_signature","submit_replication":"https://pith.science/pith/F3X3VFYPDQP4LGZKSACOO7PXYX/action/replication_record"}},"created_at":"2026-07-05T09:49:15.838058+00:00","updated_at":"2026-07-05T09:49:15.838058+00:00"}