{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GPXJKMFMZEME6LAHAWIISZDHJO","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":"4356c16f678f122b78edbf197d80c8014330c53c44e1679dc869edbaa6c33950","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T15:30:38Z","title_canon_sha256":"8e9ad768ef16afe0cd5e8a9ca86da28a379dc8265a6f9fd0ad98d579b47a1b55"},"schema_version":"1.0","source":{"id":"2608.09730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09730","created_at":"2026-08-11T02:24:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09730v1","created_at":"2026-08-11T02:24:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09730","created_at":"2026-08-11T02:24:54Z"},{"alias_kind":"pith_short_12","alias_value":"GPXJKMFMZEME","created_at":"2026-08-11T02:24:54Z"},{"alias_kind":"pith_short_16","alias_value":"GPXJKMFMZEME6LAH","created_at":"2026-08-11T02:24:54Z"},{"alias_kind":"pith_short_8","alias_value":"GPXJKMFM","created_at":"2026-08-11T02:24:54Z"}],"graph_snapshots":[{"event_id":"sha256:adcaa39bbfd5ccbaf89d489064b0a57943ef38defdae82189da8842a9615eb76","target":"graph","created_at":"2026-08-11T02:24:54Z","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/2608.09730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes evolve as a task unfolds. Recently emerging world-action models (WAMs) leverage pretrained video world models to capture spatiotemporal evolution, yet retaining future generation or a large video backbone in the control loop substantially increases inference cost. We introduce World Tokens, an embodied policy architecture built around a World Adapter that bridges visual-language understanding, world-dynamics modelin","authors_text":"Benhui Zhuang, Bo Yuan, Junlan Feng, Longteng Guo, Qu Tang, Xue Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T15:30:38Z","title":"World Tokens: Enhancing Embodied Policies with Training-Time World Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09730","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":"sha256:38a4742a5f4ebeffc39eae936e632f1955ed69faa1cbaaf6fb37a5d940636f16","target":"record","created_at":"2026-08-11T02:24:54Z","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":"4356c16f678f122b78edbf197d80c8014330c53c44e1679dc869edbaa6c33950","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T15:30:38Z","title_canon_sha256":"8e9ad768ef16afe0cd5e8a9ca86da28a379dc8265a6f9fd0ad98d579b47a1b55"},"schema_version":"1.0","source":{"id":"2608.09730","kind":"arxiv","version":1}},"canonical_sha256":"33ee9530acc9184f2c0705908964674bb1151ea98ac5b5a7c342c57e5bb99856","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33ee9530acc9184f2c0705908964674bb1151ea98ac5b5a7c342c57e5bb99856","first_computed_at":"2026-08-11T02:24:54.118088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:54.118088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NBbuibEPDaDrQTxkTB0vw3X24GpsIw2MdgnQ+/YnPyHOrhEmJf+yz7fw0QyVSg2Wqlr/bpNKA+zibupTGTyJDw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:54.119666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38a4742a5f4ebeffc39eae936e632f1955ed69faa1cbaaf6fb37a5d940636f16","sha256:adcaa39bbfd5ccbaf89d489064b0a57943ef38defdae82189da8842a9615eb76"],"state_sha256":"4afe7f71f0bb7ac0cfe5d300b6b4be1de8e139f4e91177ca244747abb86fef1b"}