{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7GHVK4566NX7FFJ7Z6TRXI2AI4","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":"50838ff99d2797e6665b6bfec42aa7cda590e9da56b31b1b09cf9e8ce93f509c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T09:35:48Z","title_canon_sha256":"424e983c76536564e2b261902cf45e9eab7ac5cf77c7b60e01636fad8029a08b"},"schema_version":"1.0","source":{"id":"2606.07089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07089","created_at":"2026-06-08T01:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07089v1","created_at":"2026-06-08T01:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07089","created_at":"2026-06-08T01:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"7GHVK4566NX7","created_at":"2026-06-08T01:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"7GHVK4566NX7FFJ7","created_at":"2026-06-08T01:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"7GHVK456","created_at":"2026-06-08T01:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:fa91b05e87306ed6d837fc1fee8b21d05b2510023b6ca440a5b8c82e8603939f","target":"graph","created_at":"2026-06-08T01:04:45Z","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/2606.07089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors and lack adaptive multimodal reasoning, limiting their effectiveness on long-horizon, complex tasks. We observe that WAMs require different multimodal reasoning modes under different execution contexts: textual reasoning is essential during task transitions to guide high-level action prediction, while visual reasoning is critical during fine-grained manipulation for precise control. Motivated by this observation, we propose \\textbf{AdaWAM}, a wo","authors_text":"Chen Gao, Jingbo Xu, Wei Wu, Yinzhou Tang, Yong Li, Yu Shang, Zihao Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T09:35:48Z","title":"Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07089","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:c9728625bbf4931d7eb61b2c9987c81b775f96857ec22d69274ab76d17a057b6","target":"record","created_at":"2026-06-08T01:04:45Z","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":"50838ff99d2797e6665b6bfec42aa7cda590e9da56b31b1b09cf9e8ce93f509c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T09:35:48Z","title_canon_sha256":"424e983c76536564e2b261902cf45e9eab7ac5cf77c7b60e01636fad8029a08b"},"schema_version":"1.0","source":{"id":"2606.07089","kind":"arxiv","version":1}},"canonical_sha256":"f98f5573bef36ff2953fcfa71ba3404711ba0b9166dedd0a959fc87060551a16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f98f5573bef36ff2953fcfa71ba3404711ba0b9166dedd0a959fc87060551a16","first_computed_at":"2026-06-08T01:04:45.612525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:45.612525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T/APEz4UtP0J/wyfHlAPd+zvsbaQC2oohikrXRsTDivqcQUCVAP4ap91z0brL1zW28CMJUxUo+wRlHpIRcK3BA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:45.613370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9728625bbf4931d7eb61b2c9987c81b775f96857ec22d69274ab76d17a057b6","sha256:fa91b05e87306ed6d837fc1fee8b21d05b2510023b6ca440a5b8c82e8603939f"],"state_sha256":"38ae45ada77b69058c025bf1cea8fab316b22c395ce73808807ccfcc2676d67c"}