{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5Z22WZ2P33RAKONONVVNJPW3M2","short_pith_number":"pith:5Z22WZ2P","schema_version":"1.0","canonical_sha256":"ee75ab674fdee20539ae6d6ad4bedb6682632e1481197a1aea94fafa1a4b0869","source":{"kind":"arxiv","id":"2607.04927","version":1},"attestation_state":"computed","paper":{"title":"DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chong Ma, Hanyang Wang, Jianjun Zhang, Jian Zhu, Kai Xie, Taiyi Su, Tianbin Liu, Tianjian Wang, Weihao Ding, Yi Xu, Youzhang He, Zhangyuan Wang, Zitai Huang","submitted_at":"2026-07-06T10:57:01Z","abstract_excerpt":"World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when household tasks involve complex multi-step goals, where coarse user commands need to be converted into sequences of fine-grained executable subtasks. Meanwhile, the field still lacks a fair real-robo"},"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":"2607.04927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-06T10:57:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5166725e9011ef9087cd8596fa0a27d4d8624c31076b297b6a70cf510f7106a7","abstract_canon_sha256":"339760892cb72e8bb449604afb9dd3d22b1ab26f71cdea31e2f946a87fcf9caf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:13.161165Z","signature_b64":"jNwrhdBLqm59JbcxGSqzzsXoW3R+ayq4gGo9+rz8DoDLcIPMSZdMl1z3aiLelJCegB/TedN8mrClPZJqOY7rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee75ab674fdee20539ae6d6ad4bedb6682632e1481197a1aea94fafa1a4b0869","last_reissued_at":"2026-07-07T02:20:13.160543Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:13.160543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chong Ma, Hanyang Wang, Jianjun Zhang, Jian Zhu, Kai Xie, Taiyi Su, Tianbin Liu, Tianjian Wang, Weihao Ding, Yi Xu, Youzhang He, Zhangyuan Wang, Zitai Huang","submitted_at":"2026-07-06T10:57:01Z","abstract_excerpt":"World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when household tasks involve complex multi-step goals, where coarse user commands need to be converted into sequences of fine-grained executable subtasks. Meanwhile, the field still lacks a fair real-robo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04927","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/2607.04927/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":"2607.04927","created_at":"2026-07-07T02:20:13.160634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04927v1","created_at":"2026-07-07T02:20:13.160634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04927","created_at":"2026-07-07T02:20:13.160634+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z22WZ2P33RA","created_at":"2026-07-07T02:20:13.160634+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z22WZ2P33RAKONO","created_at":"2026-07-07T02:20:13.160634+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z22WZ2P","created_at":"2026-07-07T02:20:13.160634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08839","citing_title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2","json":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2.json","graph_json":"https://pith.science/api/pith-number/5Z22WZ2P33RAKONONVVNJPW3M2/graph.json","events_json":"https://pith.science/api/pith-number/5Z22WZ2P33RAKONONVVNJPW3M2/events.json","paper":"https://pith.science/paper/5Z22WZ2P"},"agent_actions":{"view_html":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2","download_json":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2.json","view_paper":"https://pith.science/paper/5Z22WZ2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04927&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z22WZ2P33RAKONONVVNJPW3M2/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z22WZ2P33RAKONONVVNJPW3M2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2/action/storage_attestation","attest_author":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2/action/author_attestation","sign_citation":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2/action/citation_signature","submit_replication":"https://pith.science/pith/5Z22WZ2P33RAKONONVVNJPW3M2/action/replication_record"}},"created_at":"2026-07-07T02:20:13.160634+00:00","updated_at":"2026-07-07T02:20:13.160634+00:00"}