{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IXHBO6BEA2X32RUFEBSDTK555R","short_pith_number":"pith:IXHBO6BE","schema_version":"1.0","canonical_sha256":"45ce17782406afbd4685206439abbdec7852c3fd1e834049719de9a645f9ef05","source":{"kind":"arxiv","id":"2605.22894","version":1},"attestation_state":"computed","paper":{"title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.GR","authors_text":"Bin Li, Han Liang, Jingyan Zhang, Jingya Wang, Jingyi Yu, Juze Zhang, Lan Xu, Ruichi Zhang, Xin Chen","submitted_at":"2026-05-21T14:17:21Z","abstract_excerpt":"Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents"},"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":"2605.22894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-05-21T14:17:21Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"81efaa1501a4e829b8f5e41a65da9be7367a45a82276a66ea6f6b9ac032830d9","abstract_canon_sha256":"c33a3cd8cc3407d11ee70fd084efe0aba08a87e74c022f4073463d55618c59c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:29.062428Z","signature_b64":"9+qylRXkgwWDF4nF65AE9D371Hf+Yfr5tu+FSOPuMQ7bp0mC73Bfs2IUOkLdujegwALHiFGtrPDFYQyXCyjhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45ce17782406afbd4685206439abbdec7852c3fd1e834049719de9a645f9ef05","last_reissued_at":"2026-05-25T02:01:29.061834Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:29.061834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.GR","authors_text":"Bin Li, Han Liang, Jingyan Zhang, Jingya Wang, Jingyi Yu, Juze Zhang, Lan Xu, Ruichi Zhang, Xin Chen","submitted_at":"2026-05-21T14:17:21Z","abstract_excerpt":"Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22894","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/2605.22894/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":"2605.22894","created_at":"2026-05-25T02:01:29.061917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22894v1","created_at":"2026-05-25T02:01:29.061917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22894","created_at":"2026-05-25T02:01:29.061917+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXHBO6BEA2X3","created_at":"2026-05-25T02:01:29.061917+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXHBO6BEA2X32RUF","created_at":"2026-05-25T02:01:29.061917+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXHBO6BE","created_at":"2026-05-25T02:01:29.061917+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/IXHBO6BEA2X32RUFEBSDTK555R","json":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R.json","graph_json":"https://pith.science/api/pith-number/IXHBO6BEA2X32RUFEBSDTK555R/graph.json","events_json":"https://pith.science/api/pith-number/IXHBO6BEA2X32RUFEBSDTK555R/events.json","paper":"https://pith.science/paper/IXHBO6BE"},"agent_actions":{"view_html":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R","download_json":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R.json","view_paper":"https://pith.science/paper/IXHBO6BE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22894&json=true","fetch_graph":"https://pith.science/api/pith-number/IXHBO6BEA2X32RUFEBSDTK555R/graph.json","fetch_events":"https://pith.science/api/pith-number/IXHBO6BEA2X32RUFEBSDTK555R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R/action/storage_attestation","attest_author":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R/action/author_attestation","sign_citation":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R/action/citation_signature","submit_replication":"https://pith.science/pith/IXHBO6BEA2X32RUFEBSDTK555R/action/replication_record"}},"created_at":"2026-05-25T02:01:29.061917+00:00","updated_at":"2026-05-25T02:01:29.061917+00:00"}