{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZFRPXXZTPXSGNUYLP6UAMUZ257","short_pith_number":"pith:ZFRPXXZT","schema_version":"1.0","canonical_sha256":"c962fbdf337de466d30b7fa806533aefd145c8cc2ee4723947f304085a1002ec","source":{"kind":"arxiv","id":"2606.09215","version":1},"attestation_state":"computed","paper":{"title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jia Zheng, Junwei Liang, Shuo Yang, Teli Ma, Yudong Fan, Zifan Wang","submitted_at":"2026-06-08T08:50:14Z","abstract_excerpt":"World Action Models (WAMs) couple a video dynamics prior to the policy and have shown encouraging results on tabletop manipulation, but iterative denoising over high-dimensional video-action latents leaves them too slow for real-time humanoid loco-manipulation. The problem is compounded by the dominant hierarchical paradigm, in which a high-level manipulation policy controls only the upper body while a low-level controller tracks coarse base commands -- placing upper and lower body in inconsistent action spaces and reducing the legs to balance-preserving locomotion. We present MotionWAM, a rea"},"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":"2606.09215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-08T08:50:14Z","cross_cats_sorted":[],"title_canon_sha256":"b7f8bf7ca0bafeddd804f569d531547086b3f11465869f0e831c91bf4a3f2747","abstract_canon_sha256":"e0c5b9b3ffc1b284d3c18bf77b3161aa51bcba4c83db13f3e4791c8c99601a43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:07.678249Z","signature_b64":"7UJSJVuqTCW8UGORvnbrMUVboXV3yUjoC2qunKKeMbKDH+yp5zQrNigIzird8LxLGjpprE1WUrcNp99V7bJqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c962fbdf337de466d30b7fa806533aefd145c8cc2ee4723947f304085a1002ec","last_reissued_at":"2026-06-09T02:08:07.677713Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:07.677713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jia Zheng, Junwei Liang, Shuo Yang, Teli Ma, Yudong Fan, Zifan Wang","submitted_at":"2026-06-08T08:50:14Z","abstract_excerpt":"World Action Models (WAMs) couple a video dynamics prior to the policy and have shown encouraging results on tabletop manipulation, but iterative denoising over high-dimensional video-action latents leaves them too slow for real-time humanoid loco-manipulation. The problem is compounded by the dominant hierarchical paradigm, in which a high-level manipulation policy controls only the upper body while a low-level controller tracks coarse base commands -- placing upper and lower body in inconsistent action spaces and reducing the legs to balance-preserving locomotion. We present MotionWAM, a rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09215","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/2606.09215/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":"2606.09215","created_at":"2026-06-09T02:08:07.677798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09215v1","created_at":"2026-06-09T02:08:07.677798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09215","created_at":"2026-06-09T02:08:07.677798+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFRPXXZTPXSG","created_at":"2026-06-09T02:08:07.677798+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFRPXXZTPXSGNUYL","created_at":"2026-06-09T02:08:07.677798+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFRPXXZT","created_at":"2026-06-09T02:08:07.677798+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/ZFRPXXZTPXSGNUYLP6UAMUZ257","json":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257.json","graph_json":"https://pith.science/api/pith-number/ZFRPXXZTPXSGNUYLP6UAMUZ257/graph.json","events_json":"https://pith.science/api/pith-number/ZFRPXXZTPXSGNUYLP6UAMUZ257/events.json","paper":"https://pith.science/paper/ZFRPXXZT"},"agent_actions":{"view_html":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257","download_json":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257.json","view_paper":"https://pith.science/paper/ZFRPXXZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09215&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFRPXXZTPXSGNUYLP6UAMUZ257/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFRPXXZTPXSGNUYLP6UAMUZ257/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257/action/storage_attestation","attest_author":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257/action/author_attestation","sign_citation":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257/action/citation_signature","submit_replication":"https://pith.science/pith/ZFRPXXZTPXSGNUYLP6UAMUZ257/action/replication_record"}},"created_at":"2026-06-09T02:08:07.677798+00:00","updated_at":"2026-06-09T02:08:07.677798+00:00"}