{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WBU5L4WAMPSNHJZTTJWOWHTIND","short_pith_number":"pith:WBU5L4WA","schema_version":"1.0","canonical_sha256":"b069d5f2c063e4d3a7339a6ceb1e6868de723cc36f8ac28a5cf23b8776f5dcb3","source":{"kind":"arxiv","id":"2606.08242","version":1},"attestation_state":"computed","paper":{"title":"Light-WAM: Efficient World Action Models with State-Fusion Action Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongzhou Cheng, Jiaqi Wang, Juan Wang, Lingxuan Weng, Shiyue Wang, Xiaoyang Xu, Yibin Wang, Ziang Li","submitted_at":"2026-06-06T15:58:12Z","abstract_excerpt":"World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampl"},"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":"2606.08242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T15:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"9053dc68946502390ba8435a2b3cee4c32c9a12b2c5f0c0f14c1bf467a865831","abstract_canon_sha256":"3d65b4c3a66136a8af7a84585e4dde16a3166fca065130b9849189fc53d9abe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:31.194402Z","signature_b64":"Gy+ByoaNQyeaI+rfj7MAM5Fw8NwpZodYYyA5TqSNcXqmMMqBDGWvuMbxQQWLjqterWO8E5U28fyCJ1v8oYTdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b069d5f2c063e4d3a7339a6ceb1e6868de723cc36f8ac28a5cf23b8776f5dcb3","last_reissued_at":"2026-06-09T01:05:31.193974Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:31.193974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Light-WAM: Efficient World Action Models with State-Fusion Action Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongzhou Cheng, Jiaqi Wang, Juan Wang, Lingxuan Weng, Shiyue Wang, Xiaoyang Xu, Yibin Wang, Ziang Li","submitted_at":"2026-06-06T15:58:12Z","abstract_excerpt":"World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08242","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/2606.08242/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":"2606.08242","created_at":"2026-06-09T01:05:31.194040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08242v1","created_at":"2026-06-09T01:05:31.194040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08242","created_at":"2026-06-09T01:05:31.194040+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBU5L4WAMPSN","created_at":"2026-06-09T01:05:31.194040+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBU5L4WAMPSNHJZT","created_at":"2026-06-09T01:05:31.194040+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBU5L4WA","created_at":"2026-06-09T01:05:31.194040+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/WBU5L4WAMPSNHJZTTJWOWHTIND","json":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND.json","graph_json":"https://pith.science/api/pith-number/WBU5L4WAMPSNHJZTTJWOWHTIND/graph.json","events_json":"https://pith.science/api/pith-number/WBU5L4WAMPSNHJZTTJWOWHTIND/events.json","paper":"https://pith.science/paper/WBU5L4WA"},"agent_actions":{"view_html":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND","download_json":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND.json","view_paper":"https://pith.science/paper/WBU5L4WA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08242&json=true","fetch_graph":"https://pith.science/api/pith-number/WBU5L4WAMPSNHJZTTJWOWHTIND/graph.json","fetch_events":"https://pith.science/api/pith-number/WBU5L4WAMPSNHJZTTJWOWHTIND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND/action/storage_attestation","attest_author":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND/action/author_attestation","sign_citation":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND/action/citation_signature","submit_replication":"https://pith.science/pith/WBU5L4WAMPSNHJZTTJWOWHTIND/action/replication_record"}},"created_at":"2026-06-09T01:05:31.194040+00:00","updated_at":"2026-06-09T01:05:31.194040+00:00"}