{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e"},"schema_version":"1.0","source":{"id":"2608.08839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08839v1","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"6YPC47WC4ZDP","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"6YPC47WC4ZDPCDEY","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"6YPC47WC","created_at":"2026-08-11T01:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd","target":"graph","created_at":"2026-08-11T01:25:29Z","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/2608.08839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actions by relying mainly on visual cues rather than language instructions, since off-the-shelf text encoders embed instructions independently of visual observations. As a result, the videos predicted by these WAMs are often semantically misaligned with their corresponding language instructions, which degrades the accuracy of the predicted actions. To overcome this limitation, we propose SG-WAM, a semantic guidance method for world-action models that ","authors_text":"Haoang Li, Haodong Yan, Jiaguan Zhu, Junfeng Li, Junjie He, Ruixin Li, Shunbo Zhou, Tianran Zhang, Wen Chen, Yangyang Zheng, Yuqiao Du, Zhide Zhong","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08839","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":"sha256:4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee","target":"record","created_at":"2026-08-11T01:25:29Z","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":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e"},"schema_version":"1.0","source":{"id":"2608.08839","kind":"arxiv","version":1}},"canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","first_computed_at":"2026-08-11T01:25:29.591079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:29.591079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2UHpJt/yNNEKoKqARCG7/utmlaBfyEAVIg2CBlf8WGpa05JrCLl+HFmCBmogz3UEybwXtPeZicTtJzWk6U5YDw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:29.593761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee","sha256:a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd","sha256:7a7cd92025f5f87b7b39cb60ed21c6bbc2663d276525c6b8cb90dcb72a39180f"],"state_sha256":"d9c13c85ff08cee00106703e374158d647de37cb647d05f290869ac7cebd5f15"}