{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MNIANWN2LFZJZEK77HUGPA2WXD","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":"586085fb146f1176c9b85d5924ce838a0ed3da6a25fddfe0102fb6f890322e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T09:57:54Z","title_canon_sha256":"314676c34a684ce8e72fdcfce0cdcc61a0679d80d328505a6ede7e8ff36c8f13"},"schema_version":"1.0","source":{"id":"2608.09381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09381","created_at":"2026-08-11T02:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09381v1","created_at":"2026-08-11T02:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09381","created_at":"2026-08-11T02:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"MNIANWN2LFZJ","created_at":"2026-08-11T02:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"MNIANWN2LFZJZEK7","created_at":"2026-08-11T02:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"MNIANWN2","created_at":"2026-08-11T02:22:28Z"}],"graph_snapshots":[{"event_id":"sha256:0a4dbb4f728a6e3182dcae6a20f4fee82a7bc0b72b8c0e6495796977fad94132","target":"graph","created_at":"2026-08-11T02:22:28Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.09381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAMs avoid explicit future generation, but often compress predictive representations or separate predictive modeling from the representations used for action generation. We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor. JEPA-WAM predicts a spatially structured joint current-future target that ca","authors_text":"Cheng Chi, Chen Zhao, Jiawei He, Jing Zhang, Shifeng Bao, Xiaobo Wang, Yang Li, Yan Wang, Yihan Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T09:57:54Z","title":"JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09381","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f2fbf5676a424655fe9faf50640343ce64d65b493ae8de63e50c67e3a3c5f172","target":"record","created_at":"2026-08-11T02:22:28Z","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":"586085fb146f1176c9b85d5924ce838a0ed3da6a25fddfe0102fb6f890322e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T09:57:54Z","title_canon_sha256":"314676c34a684ce8e72fdcfce0cdcc61a0679d80d328505a6ede7e8ff36c8f13"},"schema_version":"1.0","source":{"id":"2608.09381","kind":"arxiv","version":1}},"canonical_sha256":"635006d9ba59729c915ff9e8678356b8d199b4c5b30657dd500df201c6558602","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"635006d9ba59729c915ff9e8678356b8d199b4c5b30657dd500df201c6558602","first_computed_at":"2026-08-11T02:22:28.244765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:28.244765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"psGx9FtO5cmSKrcKm1nIymDfUilVuZpyFer/1ZnzZDiqPyJaxTSCsEVNPbg7u1uaAJ5SD0guCxndJCxmZP5jCA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:28.246407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2fbf5676a424655fe9faf50640343ce64d65b493ae8de63e50c67e3a3c5f172","sha256:0a4dbb4f728a6e3182dcae6a20f4fee82a7bc0b72b8c0e6495796977fad94132"],"state_sha256":"ecab889f8df931a65f826f11fd42101871b5808c4784669ff5a33c47247fcda2"}