{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GPXJKMFMZEME6LAHAWIISZDHJO","short_pith_number":"pith:GPXJKMFM","canonical_record":{"source":{"id":"2608.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T15:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e9ad768ef16afe0cd5e8a9ca86da28a379dc8265a6f9fd0ad98d579b47a1b55","abstract_canon_sha256":"4356c16f678f122b78edbf197d80c8014330c53c44e1679dc869edbaa6c33950"},"schema_version":"1.0"},"canonical_sha256":"33ee9530acc9184f2c0705908964674bb1151ea98ac5b5a7c342c57e5bb99856","source":{"kind":"arxiv","id":"2608.09730","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GPXJKMFMZEME6LAHAWIISZDHJO","target":"record","payload":{"canonical_record":{"source":{"id":"2608.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T15:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e9ad768ef16afe0cd5e8a9ca86da28a379dc8265a6f9fd0ad98d579b47a1b55","abstract_canon_sha256":"4356c16f678f122b78edbf197d80c8014330c53c44e1679dc869edbaa6c33950"},"schema_version":"1.0"},"canonical_sha256":"33ee9530acc9184f2c0705908964674bb1151ea98ac5b5a7c342c57e5bb99856","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:54.119666Z","signature_b64":"NBbuibEPDaDrQTxkTB0vw3X24GpsIw2MdgnQ+/YnPyHOrhEmJf+yz7fw0QyVSg2Wqlr/bpNKA+zibupTGTyJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ee9530acc9184f2c0705908964674bb1151ea98ac5b5a7c342c57e5bb99856","last_reissued_at":"2026-08-11T02:24:54.118088Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:54.118088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.09730","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T02:24:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAjyrg3f59heQ4UpGaTCKgaIdvCpp8zcsyVTaQGPo1eHe0ZbLHWtArNDjREe9BdQjcJ56unwLRRH8rGnKzbcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:12:48.706652Z"},"content_sha256":"38a4742a5f4ebeffc39eae936e632f1955ed69faa1cbaaf6fb37a5d940636f16","schema_version":"1.0","event_id":"sha256:38a4742a5f4ebeffc39eae936e632f1955ed69faa1cbaaf6fb37a5d940636f16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GPXJKMFMZEME6LAHAWIISZDHJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"World Tokens: Enhancing Embodied Policies with Training-Time World Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benhui Zhuang, Bo Yuan, Junlan Feng, Longteng Guo, Qu Tang, Xue Yu","submitted_at":"2026-08-10T15:30:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09730","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/2608.09730/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T02:24:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M9k3XeOspvUZfTuAMt1OOxPlDr0hW+HsPQs4bSlIGaohavvtiTRIYtUgJ/s/NzqxoRn5ThvzljTqO8PlRTeDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:12:48.707179Z"},"content_sha256":"adcaa39bbfd5ccbaf89d489064b0a57943ef38defdae82189da8842a9615eb76","schema_version":"1.0","event_id":"sha256:adcaa39bbfd5ccbaf89d489064b0a57943ef38defdae82189da8842a9615eb76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPXJKMFMZEME6LAHAWIISZDHJO/bundle.json","state_url":"https://pith.science/pith/GPXJKMFMZEME6LAHAWIISZDHJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPXJKMFMZEME6LAHAWIISZDHJO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T00:12:48Z","links":{"resolver":"https://pith.science/pith/GPXJKMFMZEME6LAHAWIISZDHJO","bundle":"https://pith.science/pith/GPXJKMFMZEME6LAHAWIISZDHJO/bundle.json","state":"https://pith.science/pith/GPXJKMFMZEME6LAHAWIISZDHJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPXJKMFMZEME6LAHAWIISZDHJO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9NjGomSJNDO4qO5nb1vJ0Q9RvFqGNj9KQvvtOmK1jM5WM7Km6Z3xk2zBiXBsbpc3D9mAXdnGPhUrRS1zggbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T00:12:48.711036Z","bundle_sha256":"f13537b6e301c6d7480d8d340749ac6fedd1614e7a470d202c5d6be8b28aa650"}}