{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SLZ2NTRGAIFUE5IR4DN5V5YZON","short_pith_number":"pith:SLZ2NTRG","schema_version":"1.0","canonical_sha256":"92f3a6ce26020b427511e0dbdaf719735e80d1f81a4e531494302d0bbd89469c","source":{"kind":"arxiv","id":"2607.28993","version":1},"attestation_state":"computed","paper":{"title":"ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bin Hu, Bin Qian, Bowen Jing, Enyi Wang, Feng Yan, Haoning Wu, Houde Liu, Kaitao Jiang, Kangning Niu, Mingxin Wang, Mu Xu, Ruiyang Hao, Tianlun Li, Yandan Yang, Yan Wang","submitted_at":"2026-07-31T03:44:56Z","abstract_excerpt":"World Action Models (WAMs) have emerged as a promising paradigm by jointly modeling robot actions and future visual dynamics. However, their reliance on pixel-generative future supervision can entangle action-relevant state transitions with task-irrelevant visual content, limiting robustness under visual distribution shifts. We identify Training-Distribution Hallucination, a recurring phenomenon in which futures conditioned on visually shifted observations hallucinate training-domain content rather than remain faithful to the current scene. A controlled frame-triplet diagnosis further shows th"},"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":"2607.28993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T03:44:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4cd396d34a5ca86fb6ec8e8ead57d0f7bcc796b02655d6f1245d583a04e6d173","abstract_canon_sha256":"0a1f38a5b346609bc3b5015b4fd14a803e4ff76650e1db71372000582154ffcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:17:52.818394Z","signature_b64":"cNJML5SXpE4vXMuTeJsVTy4NIIL3Nd5eIka9AbdD0e4o4275OU6ag18MFuToKmF7GG+rFAJDueVZSDepWOhxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92f3a6ce26020b427511e0dbdaf719735e80d1f81a4e531494302d0bbd89469c","last_reissued_at":"2026-08-03T01:17:52.816968Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:17:52.816968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bin Hu, Bin Qian, Bowen Jing, Enyi Wang, Feng Yan, Haoning Wu, Houde Liu, Kaitao Jiang, Kangning Niu, Mingxin Wang, Mu Xu, Ruiyang Hao, Tianlun Li, Yandan Yang, Yan Wang","submitted_at":"2026-07-31T03:44:56Z","abstract_excerpt":"World Action Models (WAMs) have emerged as a promising paradigm by jointly modeling robot actions and future visual dynamics. However, their reliance on pixel-generative future supervision can entangle action-relevant state transitions with task-irrelevant visual content, limiting robustness under visual distribution shifts. We identify Training-Distribution Hallucination, a recurring phenomenon in which futures conditioned on visually shifted observations hallucinate training-domain content rather than remain faithful to the current scene. A controlled frame-triplet diagnosis further shows th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28993","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/2607.28993/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":"2607.28993","created_at":"2026-08-03T01:17:52.817868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28993v1","created_at":"2026-08-03T01:17:52.817868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28993","created_at":"2026-08-03T01:17:52.817868+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLZ2NTRGAIFU","created_at":"2026-08-03T01:17:52.817868+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLZ2NTRGAIFUE5IR","created_at":"2026-08-03T01:17:52.817868+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLZ2NTRG","created_at":"2026-08-03T01:17:52.817868+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/SLZ2NTRGAIFUE5IR4DN5V5YZON","json":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON.json","graph_json":"https://pith.science/api/pith-number/SLZ2NTRGAIFUE5IR4DN5V5YZON/graph.json","events_json":"https://pith.science/api/pith-number/SLZ2NTRGAIFUE5IR4DN5V5YZON/events.json","paper":"https://pith.science/paper/SLZ2NTRG"},"agent_actions":{"view_html":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON","download_json":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON.json","view_paper":"https://pith.science/paper/SLZ2NTRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28993&json=true","fetch_graph":"https://pith.science/api/pith-number/SLZ2NTRGAIFUE5IR4DN5V5YZON/graph.json","fetch_events":"https://pith.science/api/pith-number/SLZ2NTRGAIFUE5IR4DN5V5YZON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON/action/storage_attestation","attest_author":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON/action/author_attestation","sign_citation":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON/action/citation_signature","submit_replication":"https://pith.science/pith/SLZ2NTRGAIFUE5IR4DN5V5YZON/action/replication_record"}},"created_at":"2026-08-03T01:17:52.817868+00:00","updated_at":"2026-08-03T01:17:52.817868+00:00"}