{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UXJ42TQHSZHUD3OHQVLWROTH3C","short_pith_number":"pith:UXJ42TQH","schema_version":"1.0","canonical_sha256":"a5d3cd4e07964f41edc7855768ba67d8856925b6c8bdb524a8b0554ae3f836b7","source":{"kind":"arxiv","id":"2407.06141","version":2},"attestation_state":"computed","paper":{"title":"CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Harry Zhang, Luca Carlone","submitted_at":"2024-05-27T02:42:38Z","abstract_excerpt":"We introduce CHAMP, a novel method for learning sequence-to-sequence, multi-hypothesis 3D human poses from 2D keypoints by leveraging a conditional distribution with a diffusion model. To predict a single output 3D pose sequence, we generate and aggregate multiple 3D pose hypotheses. For better aggregation results, we develop a method to score these hypotheses during training, effectively integrating conformal prediction into the learning process. This process results in a differentiable conformal predictor that is trained end2end with the 3D pose estimator. Post-training, the learned scoring "},"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":"2407.06141","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T02:42:38Z","cross_cats_sorted":[],"title_canon_sha256":"fcdb08619293de79bcf5643df025a6f3ee7a5732270e710f553777b0ca834083","abstract_canon_sha256":"d9c6449e3e7f258e4af64833ce75bbe037fdcd6c73b6265296ed9d912639b545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:39.321521Z","signature_b64":"OHyWc9WTdPHoeIcFj5rcMzommeqDJsOnqfEmS1lV0Y1XcKhyjjrDWTnXqkr2OSvnwTj025LyWSNgd8Swsio4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d3cd4e07964f41edc7855768ba67d8856925b6c8bdb524a8b0554ae3f836b7","last_reissued_at":"2026-07-05T10:18:39.320964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:39.320964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Harry Zhang, Luca Carlone","submitted_at":"2024-05-27T02:42:38Z","abstract_excerpt":"We introduce CHAMP, a novel method for learning sequence-to-sequence, multi-hypothesis 3D human poses from 2D keypoints by leveraging a conditional distribution with a diffusion model. To predict a single output 3D pose sequence, we generate and aggregate multiple 3D pose hypotheses. For better aggregation results, we develop a method to score these hypotheses during training, effectively integrating conformal prediction into the learning process. This process results in a differentiable conformal predictor that is trained end2end with the 3D pose estimator. Post-training, the learned scoring "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06141","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/2407.06141/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":"2407.06141","created_at":"2026-07-05T10:18:39.321024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06141v2","created_at":"2026-07-05T10:18:39.321024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06141","created_at":"2026-07-05T10:18:39.321024+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXJ42TQHSZHU","created_at":"2026-07-05T10:18:39.321024+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXJ42TQHSZHUD3OH","created_at":"2026-07-05T10:18:39.321024+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXJ42TQH","created_at":"2026-07-05T10:18:39.321024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10431","citing_title":"CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C","json":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C.json","graph_json":"https://pith.science/api/pith-number/UXJ42TQHSZHUD3OHQVLWROTH3C/graph.json","events_json":"https://pith.science/api/pith-number/UXJ42TQHSZHUD3OHQVLWROTH3C/events.json","paper":"https://pith.science/paper/UXJ42TQH"},"agent_actions":{"view_html":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C","download_json":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C.json","view_paper":"https://pith.science/paper/UXJ42TQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06141&json=true","fetch_graph":"https://pith.science/api/pith-number/UXJ42TQHSZHUD3OHQVLWROTH3C/graph.json","fetch_events":"https://pith.science/api/pith-number/UXJ42TQHSZHUD3OHQVLWROTH3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C/action/storage_attestation","attest_author":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C/action/author_attestation","sign_citation":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C/action/citation_signature","submit_replication":"https://pith.science/pith/UXJ42TQHSZHUD3OHQVLWROTH3C/action/replication_record"}},"created_at":"2026-07-05T10:18:39.321024+00:00","updated_at":"2026-07-05T10:18:39.321024+00:00"}