{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:INWGUDQRYMH2UEVOORBIH44KKI","short_pith_number":"pith:INWGUDQR","schema_version":"1.0","canonical_sha256":"436c6a0e11c30faa12ae744283f38a520a0bf409ece3682377ae28e24f8623ff","source":{"kind":"arxiv","id":"2602.06827","version":3},"attestation_state":"computed","paper":{"title":"DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sampling-based trajectory optimization refines human motions into dynamically feasible humanoid loco-manipulation sequences.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Angela Dai, Dian Yu, Ilyass Taouil, Kun Tao, Majid Khadiv, Shafeef Omar, Victor Dhedin","submitted_at":"2026-02-06T16:14:27Z","abstract_excerpt":"In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framew"},"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":"2602.06827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T16:14:27Z","cross_cats_sorted":[],"title_canon_sha256":"c9aee8bbb76102714b7a8bd8e088a62f94afc2eff7b07614b9637381d3d841d5","abstract_canon_sha256":"2cbf15fbff7a8fae8010bd66bd082f368badc26dc7a647a7c92a70bf9be449ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:32.776025Z","signature_b64":"4j9/iYcHkJa7+PnOo2KRC3G2Q7fRty4eyooYZzscvIxS5gTQrZPjY65M+HFRahy3JwdHdoZU3bHeHZp+oTA7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436c6a0e11c30faa12ae744283f38a520a0bf409ece3682377ae28e24f8623ff","last_reissued_at":"2026-06-11T01:10:32.775070Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:32.775070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sampling-based trajectory optimization refines human motions into dynamically feasible humanoid loco-manipulation sequences.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Angela Dai, Dian Yu, Ilyass Taouil, Kun Tao, Majid Khadiv, Shafeef Omar, Victor Dhedin","submitted_at":"2026-02-06T16:14:27Z","abstract_excerpt":"In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framew"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the sampling-based trajectory optimization can reliably discover dynamically feasible solutions for long-horizon tasks without excessive computation time or getting trapped in infeasible regions for complex object interactions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DynaRetarget refines human kinematic motions into dynamically feasible humanoid trajectories using incremental sampling-based trajectory optimization, achieving higher success rates than prior methods on diverse object interaction tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sampling-based trajectory optimization refines human motions into dynamically feasible humanoid loco-manipulation sequences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cd80f079679372d209ee690b4e754091170e2d1a47272b906de7e13c48fa89f9"},"source":{"id":"2602.06827","kind":"arxiv","version":3},"verdict":{"id":"5ffccf44-4f16-44b4-8212-cb11e447d9e9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:43:11.742489Z","strongest_claim":"We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective.","one_line_summary":"DynaRetarget refines human kinematic motions into dynamically feasible humanoid trajectories using incremental sampling-based trajectory optimization, achieving higher success rates than prior methods on diverse object interaction tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the sampling-based trajectory optimization can reliably discover dynamically feasible solutions for long-horizon tasks without excessive computation time or getting trapped in infeasible regions for complex object interactions.","pith_extraction_headline":"Sampling-based trajectory optimization refines human motions into dynamically feasible humanoid loco-manipulation sequences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.06827/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":"2602.06827","created_at":"2026-06-11T01:10:32.775202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06827v3","created_at":"2026-06-11T01:10:32.775202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06827","created_at":"2026-06-11T01:10:32.775202+00:00"},{"alias_kind":"pith_short_12","alias_value":"INWGUDQRYMH2","created_at":"2026-06-11T01:10:32.775202+00:00"},{"alias_kind":"pith_short_16","alias_value":"INWGUDQRYMH2UEVO","created_at":"2026-06-11T01:10:32.775202+00:00"},{"alias_kind":"pith_short_8","alias_value":"INWGUDQR","created_at":"2026-06-11T01:10:32.775202+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/INWGUDQRYMH2UEVOORBIH44KKI","json":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI.json","graph_json":"https://pith.science/api/pith-number/INWGUDQRYMH2UEVOORBIH44KKI/graph.json","events_json":"https://pith.science/api/pith-number/INWGUDQRYMH2UEVOORBIH44KKI/events.json","paper":"https://pith.science/paper/INWGUDQR"},"agent_actions":{"view_html":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI","download_json":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI.json","view_paper":"https://pith.science/paper/INWGUDQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06827&json=true","fetch_graph":"https://pith.science/api/pith-number/INWGUDQRYMH2UEVOORBIH44KKI/graph.json","fetch_events":"https://pith.science/api/pith-number/INWGUDQRYMH2UEVOORBIH44KKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI/action/storage_attestation","attest_author":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI/action/author_attestation","sign_citation":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI/action/citation_signature","submit_replication":"https://pith.science/pith/INWGUDQRYMH2UEVOORBIH44KKI/action/replication_record"}},"created_at":"2026-06-11T01:10:32.775202+00:00","updated_at":"2026-06-11T01:10:32.775202+00:00"}