{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JQ77BRSB5EVK2AXA7MBCAAUPZG","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":"cf76c07b1f961cd1fd787301b3d6a9a85ebd6c0cc6a5bd1cfff93cc413c72a47","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-18T17:05:19Z","title_canon_sha256":"2ffc77d956ddc15453ab8b26e45a1aac7b41a4ad4be7af820380f9fb62e7067b"},"schema_version":"1.0","source":{"id":"2606.20781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20781","created_at":"2026-06-23T00:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20781v1","created_at":"2026-06-23T00:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20781","created_at":"2026-06-23T00:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"JQ77BRSB5EVK","created_at":"2026-06-23T00:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"JQ77BRSB5EVK2AXA","created_at":"2026-06-23T00:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"JQ77BRSB","created_at":"2026-06-23T00:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:cc43a12bb12e40a4f3e4cf88649abb46ff150e92e517796d7e923c602843ae8f","target":"graph","created_at":"2026-06-23T00:11:56Z","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/2606.20781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core. This rapid expansion has blurred the boundary among broad world models, video generation models, action-grounded video world models, Vision-Language-Action policies, and WAMs. This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views. The","authors_text":"Qi Li, Qiuhong Shen, Shihua Zhang, Shizun Wang, Shuicheng Yan, Xinchao Wang, Yue Liao, Zhenxiong Tan","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-18T17:05:19Z","title":"World Action Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20781","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:a8589ca5ccab1072322881683e4be1a92b772ff054bd6e45ed7f99121fbfdb5d","target":"record","created_at":"2026-06-23T00:11:56Z","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":"cf76c07b1f961cd1fd787301b3d6a9a85ebd6c0cc6a5bd1cfff93cc413c72a47","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-18T17:05:19Z","title_canon_sha256":"2ffc77d956ddc15453ab8b26e45a1aac7b41a4ad4be7af820380f9fb62e7067b"},"schema_version":"1.0","source":{"id":"2606.20781","kind":"arxiv","version":1}},"canonical_sha256":"4c3ff0c641e92aad02e0fb0220028fc9bccbb2426af299159253064288bead61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c3ff0c641e92aad02e0fb0220028fc9bccbb2426af299159253064288bead61","first_computed_at":"2026-06-23T00:11:56.639173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:56.639173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+G5/uZ7oSkHKf3i+fn2lb1kLUWeBwCdtXmN86njrCvZ0mdY2T9tvF/0jh8EKKLO8BHnWD57ozbtN98w7OjYwAw==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:56.639593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8589ca5ccab1072322881683e4be1a92b772ff054bd6e45ed7f99121fbfdb5d","sha256:cc43a12bb12e40a4f3e4cf88649abb46ff150e92e517796d7e923c602843ae8f"],"state_sha256":"ee5029a31185af23fd72bf06896a039615a9e951ed559bbcde67ebc686354dc0"}