{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","short_pith_number":"pith:6YPC47WC","schema_version":"1.0","canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","source":{"kind":"arxiv","id":"2608.08839","version":1},"attestation_state":"computed","paper":{"title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","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","submitted_at":"2026-08-09T17:59:35Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.08839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e","abstract_canon_sha256":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:25:29.593761Z","signature_b64":"2UHpJt/yNNEKoKqARCG7/utmlaBfyEAVIg2CBlf8WGpa05JrCLl+HFmCBmogz3UEybwXtPeZicTtJzWk6U5YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","last_reissued_at":"2026-08-11T01:25:29.591079Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:25:29.591079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","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","submitted_at":"2026-08-09T17:59:35Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08839","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/2608.08839/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.08839","created_at":"2026-08-11T01:25:29.592105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08839v1","created_at":"2026-08-11T01:25:29.592105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08839","created_at":"2026-08-11T01:25:29.592105+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YPC47WC4ZDP","created_at":"2026-08-11T01:25:29.592105+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YPC47WC4ZDPCDEY","created_at":"2026-08-11T01:25:29.592105+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YPC47WC","created_at":"2026-08-11T01:25:29.592105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH","json":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH.json","graph_json":"https://pith.science/api/pith-number/6YPC47WC4ZDPCDEYK7LDLVHLWH/graph.json","events_json":"https://pith.science/api/pith-number/6YPC47WC4ZDPCDEYK7LDLVHLWH/events.json","paper":"https://pith.science/paper/6YPC47WC"},"agent_actions":{"view_html":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH","download_json":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH.json","view_paper":"https://pith.science/paper/6YPC47WC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08839&json=true","fetch_graph":"https://pith.science/api/pith-number/6YPC47WC4ZDPCDEYK7LDLVHLWH/graph.json","fetch_events":"https://pith.science/api/pith-number/6YPC47WC4ZDPCDEYK7LDLVHLWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/action/storage_attestation","attest_author":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/action/author_attestation","sign_citation":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/action/citation_signature","submit_replication":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/action/replication_record"}},"created_at":"2026-08-11T01:25:29.592105+00:00","updated_at":"2026-08-11T01:25:29.592105+00:00"}