{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4WTWMSAYMO7SDAKREQNWIJIWT5","short_pith_number":"pith:4WTWMSAY","schema_version":"1.0","canonical_sha256":"e5a766481863bf218151241b6425169f7e6487b29102d63253d30b638b01d6af","source":{"kind":"arxiv","id":"2606.19531","version":1},"attestation_state":"computed","paper":{"title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Haitao Lin, He Zhang, Jingbo Zhang, Wenjun Zeng, Wenyao Zhang, Xiaokang Yang, Xin Jin, Yao Mu, Yuyang Zhang, Zekun Qi","submitted_at":"2026-06-17T19:25:28Z","abstract_excerpt":"World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot "},"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":"2606.19531","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:25:28Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e7fe8a3a9f8f506548205193313f05dcdd0804084e79ca5380bcc18bc1bff75c","abstract_canon_sha256":"14dff20fdbfd8b29e391a49c84506d79e40b88c9b6f2b5befe6d6df2f7de52ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:27.958120Z","signature_b64":"JbFBwzKDqQYTJjItvfaomg0BbQyihnVljm8FC6FymKz8FO8BenGmqBzlkdHPU9YcbnO94guc6759D5nV+oE+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5a766481863bf218151241b6425169f7e6487b29102d63253d30b638b01d6af","last_reissued_at":"2026-06-19T16:12:27.957770Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:27.957770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Haitao Lin, He Zhang, Jingbo Zhang, Wenjun Zeng, Wenyao Zhang, Xiaokang Yang, Xin Jin, Yao Mu, Yuyang Zhang, Zekun Qi","submitted_at":"2026-06-17T19:25:28Z","abstract_excerpt":"World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19531","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/2606.19531/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":"2606.19531","created_at":"2026-06-19T16:12:27.957834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19531v1","created_at":"2026-06-19T16:12:27.957834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19531","created_at":"2026-06-19T16:12:27.957834+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WTWMSAYMO7S","created_at":"2026-06-19T16:12:27.957834+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WTWMSAYMO7SDAKR","created_at":"2026-06-19T16:12:27.957834+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WTWMSAY","created_at":"2026-06-19T16:12:27.957834+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/4WTWMSAYMO7SDAKREQNWIJIWT5","json":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5.json","graph_json":"https://pith.science/api/pith-number/4WTWMSAYMO7SDAKREQNWIJIWT5/graph.json","events_json":"https://pith.science/api/pith-number/4WTWMSAYMO7SDAKREQNWIJIWT5/events.json","paper":"https://pith.science/paper/4WTWMSAY"},"agent_actions":{"view_html":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5","download_json":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5.json","view_paper":"https://pith.science/paper/4WTWMSAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19531&json=true","fetch_graph":"https://pith.science/api/pith-number/4WTWMSAYMO7SDAKREQNWIJIWT5/graph.json","fetch_events":"https://pith.science/api/pith-number/4WTWMSAYMO7SDAKREQNWIJIWT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5/action/storage_attestation","attest_author":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5/action/author_attestation","sign_citation":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5/action/citation_signature","submit_replication":"https://pith.science/pith/4WTWMSAYMO7SDAKREQNWIJIWT5/action/replication_record"}},"created_at":"2026-06-19T16:12:27.957834+00:00","updated_at":"2026-06-19T16:12:27.957834+00:00"}