{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TQIHEVKTCMXGFPQOUJFI6XN6C2","short_pith_number":"pith:TQIHEVKT","canonical_record":{"source":{"id":"2604.28130","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:16:38Z","cross_cats_sorted":[],"title_canon_sha256":"8fe5d93a1a05045be4b6b0ef06cd2d0f8ca80d829a6350895c30f3687f1b02d8","abstract_canon_sha256":"cd97f7be77a3cc9ba7da53d1d89d6ebd75215559d540f8505b759410c1c6863c"},"schema_version":"1.0"},"canonical_sha256":"9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36","source":{"kind":"arxiv","id":"2604.28130","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.28130","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.28130v3","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.28130","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"TQIHEVKTCMXG","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"TQIHEVKTCMXGFPQO","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"TQIHEVKT","created_at":"2026-06-23T01:12:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TQIHEVKTCMXGFPQOUJFI6XN6C2","target":"record","payload":{"canonical_record":{"source":{"id":"2604.28130","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:16:38Z","cross_cats_sorted":[],"title_canon_sha256":"8fe5d93a1a05045be4b6b0ef06cd2d0f8ca80d829a6350895c30f3687f1b02d8","abstract_canon_sha256":"cd97f7be77a3cc9ba7da53d1d89d6ebd75215559d540f8505b759410c1c6863c"},"schema_version":"1.0"},"canonical_sha256":"9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:07.786648Z","signature_b64":"RJNRz151QmET3VCyK0toSaOygFbKWJhHha1sYjHTTjJ+Q+6+V+hJlnXvOMSLSM/yQlyiqVRJ/x4SPX+cuROqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36","last_reissued_at":"2026-06-23T01:12:07.786075Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:07.786075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.28130","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQTy5iy7ct66gxVnA6aOvL29uXTjzRFZI4P5NtpBqDZIUStn790VyMR6qibd53M1V5LbhnW0olghIyzSDsHHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:15:14.805283Z"},"content_sha256":"b07cb6aef3b996290548a203a195a62d2185ff8e644b97984d6bd659352f1c36","schema_version":"1.0","event_id":"sha256:b07cb6aef3b996290548a203a195a62d2185ff8e644b97984d6bd659352f1c36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TQIHEVKTCMXGFPQOUJFI6XN6C2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dao Thien Phong, Dongze Lian, Guanli Hou, Hanwang Zhang, Kehong Gong, Mingxi Xu, Mingyuan Zhang, Ning Zhang, Qi Wang, Weixia He, Xiaoyu He, Zhengyu Li, Zhengyu Wen","submitted_at":"2026-04-30T17:16:38Z","abstract_excerpt":"Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end fram"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized... Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That supplying one reference pose-rotation pair from the target asset, together with the rest pose, is sufficient to uniquely anchor the rotation coordinate system and enable effective learning across arbitrary unseen skeletons without additional constraints or post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A fully differentiable end-to-end model for arbitrary-skeleton motion capture from video that jointly learns pose estimation and rotation recovery using reference pose-rotation pairs to eliminate IK ambiguities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b2714845b518cf6e55ac2f47988e8854d48044cd4f4cdb942c533f1c819837bf"},"source":{"id":"2604.28130","kind":"arxiv","version":3},"verdict":{"id":"ffb9226e-1ffe-434d-a502-3744c97faf49","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:33:14.193413Z","strongest_claim":"we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized... Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines.","one_line_summary":"A fully differentiable end-to-end model for arbitrary-skeleton motion capture from video that jointly learns pose estimation and rotation recovery using reference pose-rotation pairs to eliminate IK ambiguities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That supplying one reference pose-rotation pair from the target asset, together with the rest pose, is sufficient to uniquely anchor the rotation coordinate system and enable effective learning across arbitrary unseen skeletons without additional constraints or post-processing.","pith_extraction_headline":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.28130/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:40:29.991002Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:36:33.297709Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6857971580c1f0e149d52277cfc842dcd66502280aa15119f5d29412abb6d283"},"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"},"verdict_id":"ffb9226e-1ffe-434d-a502-3744c97faf49"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNxCRIJc9wts99qTaj5bsoF95DpCpD1rkMJmgQiBYtSaDsUU2f4uHTSQSKImfeLHOS7MhW12oBsQKPwU4mWGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:15:14.806186Z"},"content_sha256":"ae29392c2989ca46b71d8ce59211c63408945ade02e6d3c3262d3900026b9b2f","schema_version":"1.0","event_id":"sha256:ae29392c2989ca46b71d8ce59211c63408945ade02e6d3c3262d3900026b9b2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/bundle.json","state_url":"https://pith.science/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:15:14Z","links":{"resolver":"https://pith.science/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2","bundle":"https://pith.science/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/bundle.json","state":"https://pith.science/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQIHEVKTCMXGFPQOUJFI6XN6C2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TQIHEVKTCMXGFPQOUJFI6XN6C2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd97f7be77a3cc9ba7da53d1d89d6ebd75215559d540f8505b759410c1c6863c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:16:38Z","title_canon_sha256":"8fe5d93a1a05045be4b6b0ef06cd2d0f8ca80d829a6350895c30f3687f1b02d8"},"schema_version":"1.0","source":{"id":"2604.28130","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.28130","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.28130v3","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.28130","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"TQIHEVKTCMXG","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"TQIHEVKTCMXGFPQO","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"TQIHEVKT","created_at":"2026-06-23T01:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:ae29392c2989ca46b71d8ce59211c63408945ade02e6d3c3262d3900026b9b2f","target":"graph","created_at":"2026-06-23T01:12:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized... Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That supplying one reference pose-rotation pair from the target asset, together with the rest pose, is sufficient to uniquely anchor the rotation coordinate system and enable effective learning across arbitrary unseen skeletons without additional constraints or post-processing."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A fully differentiable end-to-end model for arbitrary-skeleton motion capture from video that jointly learns pose estimation and rotation recovery using reference pose-rotation pairs to eliminate IK ambiguities."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton."}],"snapshot_sha256":"b2714845b518cf6e55ac2f47988e8854d48044cd4f4cdb942c533f1c819837bf"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T20:40:29.991002Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:36:33.297709Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.28130/integrity.json","findings":[],"snapshot_sha256":"6857971580c1f0e149d52277cfc842dcd66502280aa15119f5d29412abb6d283","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end fram","authors_text":"Dao Thien Phong, Dongze Lian, Guanli Hou, Hanwang Zhang, Kehong Gong, Mingxi Xu, Mingyuan Zhang, Ning Zhang, Qi Wang, Weixia He, Xiaoyu He, Zhengyu Li, Zhengyu Wen","cross_cats":[],"headline":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:16:38Z","title":"MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.28130","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T06:33:14.193413Z","id":"ffb9226e-1ffe-434d-a502-3744c97faf49","model_set":{"reader":"grok-4.3"},"one_line_summary":"A fully differentiable end-to-end model for arbitrary-skeleton motion capture from video that jointly learns pose estimation and rotation recovery using reference pose-rotation pairs to eliminate IK ambiguities.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton.","strongest_claim":"we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized... Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines.","weakest_assumption":"That supplying one reference pose-rotation pair from the target asset, together with the rest pose, is sufficient to uniquely anchor the rotation coordinate system and enable effective learning across arbitrary unseen skeletons without additional constraints or post-processing."}},"verdict_id":"ffb9226e-1ffe-434d-a502-3744c97faf49"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b07cb6aef3b996290548a203a195a62d2185ff8e644b97984d6bd659352f1c36","target":"record","created_at":"2026-06-23T01:12:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cd97f7be77a3cc9ba7da53d1d89d6ebd75215559d540f8505b759410c1c6863c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:16:38Z","title_canon_sha256":"8fe5d93a1a05045be4b6b0ef06cd2d0f8ca80d829a6350895c30f3687f1b02d8"},"schema_version":"1.0","source":{"id":"2604.28130","kind":"arxiv","version":3}},"canonical_sha256":"9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36","first_computed_at":"2026-06-23T01:12:07.786075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:07.786075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RJNRz151QmET3VCyK0toSaOygFbKWJhHha1sYjHTTjJ+Q+6+V+hJlnXvOMSLSM/yQlyiqVRJ/x4SPX+cuROqCw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:07.786648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.28130","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b07cb6aef3b996290548a203a195a62d2185ff8e644b97984d6bd659352f1c36","sha256:ae29392c2989ca46b71d8ce59211c63408945ade02e6d3c3262d3900026b9b2f"],"state_sha256":"eb7305be6c5f584dd4abb4a9b631de5da3648e16f154bf0513f9f15b7e46191b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhFp1r3awCwTpEZSdKHa5bma68nHXDMh8yV5mCctVA5XL+s3FI737RS11SBrfZClXk/Trc7wlY6sVKOOvJMXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:15:14.810437Z","bundle_sha256":"eafad2fa9728dfe7219e192694ed3eeee4c8dd092bb70eb45e394365e712e302"}}