{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FI5WRRGP4EOASWHGJXOURBVCER","short_pith_number":"pith:FI5WRRGP","schema_version":"1.0","canonical_sha256":"2a3b68c4cfe11c0958e64ddd4886a22467a75010e36f07541c180e431a388764","source":{"kind":"arxiv","id":"2304.03274","version":2},"attestation_state":"computed","paper":{"title":"DiffMimic: Efficient Motion Mimicking with Differentiable Physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cunjun Yu, Jiawei Ren, Liang Pan, Siwei Chen, Xiao Ma, Ziwei Liu","submitted_at":"2023-04-06T17:56:22Z","abstract_excerpt":"Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow convergence with hard explorations. Specifically, they usually take tens of hours or even days of training to mimic a simple motion sequence, resulting in poor scalability. In this work, we leverage differentiable physics simulators (DPS) and propose an efficient motion mimicking method dubbed DiffMimic. Our key insight is that DPS casts a complex policy learning"},"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":"2304.03274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T17:56:22Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"744a72cee9925c38b9fa2224b8113d1c0487dd3631ca7d55ee3131d5d1886bb1","abstract_canon_sha256":"0d846befa116883f5a6f9f8903df0c415376b2a9934ee1e9c1cafaa56dde5cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:37.784986Z","signature_b64":"AkX2i4BgYyqjALwgXnPgj3lWLzKw1I3R1ZPU3X7yZ/G3/z10S2rutXoDXtA4kGpnZsz9cJDgyw498GgDFoQnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3b68c4cfe11c0958e64ddd4886a22467a75010e36f07541c180e431a388764","last_reissued_at":"2026-07-05T06:04:37.784595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:37.784595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffMimic: Efficient Motion Mimicking with Differentiable Physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cunjun Yu, Jiawei Ren, Liang Pan, Siwei Chen, Xiao Ma, Ziwei Liu","submitted_at":"2023-04-06T17:56:22Z","abstract_excerpt":"Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow convergence with hard explorations. Specifically, they usually take tens of hours or even days of training to mimic a simple motion sequence, resulting in poor scalability. In this work, we leverage differentiable physics simulators (DPS) and propose an efficient motion mimicking method dubbed DiffMimic. Our key insight is that DPS casts a complex policy learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03274","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/2304.03274/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":"2304.03274","created_at":"2026-07-05T06:04:37.784644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03274v2","created_at":"2026-07-05T06:04:37.784644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03274","created_at":"2026-07-05T06:04:37.784644+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI5WRRGP4EOA","created_at":"2026-07-05T06:04:37.784644+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI5WRRGP4EOASWHG","created_at":"2026-07-05T06:04:37.784644+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI5WRRGP","created_at":"2026-07-05T06:04:37.784644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06094","citing_title":"Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07984","citing_title":"Physics-Based Motion Tracking of Contact-Rich Interacting Characters","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER","json":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER.json","graph_json":"https://pith.science/api/pith-number/FI5WRRGP4EOASWHGJXOURBVCER/graph.json","events_json":"https://pith.science/api/pith-number/FI5WRRGP4EOASWHGJXOURBVCER/events.json","paper":"https://pith.science/paper/FI5WRRGP"},"agent_actions":{"view_html":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER","download_json":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER.json","view_paper":"https://pith.science/paper/FI5WRRGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03274&json=true","fetch_graph":"https://pith.science/api/pith-number/FI5WRRGP4EOASWHGJXOURBVCER/graph.json","fetch_events":"https://pith.science/api/pith-number/FI5WRRGP4EOASWHGJXOURBVCER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER/action/storage_attestation","attest_author":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER/action/author_attestation","sign_citation":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER/action/citation_signature","submit_replication":"https://pith.science/pith/FI5WRRGP4EOASWHGJXOURBVCER/action/replication_record"}},"created_at":"2026-07-05T06:04:37.784644+00:00","updated_at":"2026-07-05T06:04:37.784644+00:00"}