{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4WTWMSAYMO7SDAKREQNWIJIWT5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"14dff20fdbfd8b29e391a49c84506d79e40b88c9b6f2b5befe6d6df2f7de52ae","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:25:28Z","title_canon_sha256":"e7fe8a3a9f8f506548205193313f05dcdd0804084e79ca5380bcc18bc1bff75c"},"schema_version":"1.0","source":{"id":"2606.19531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19531","created_at":"2026-06-19T16:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19531v1","created_at":"2026-06-19T16:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19531","created_at":"2026-06-19T16:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"4WTWMSAYMO7S","created_at":"2026-06-19T16:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"4WTWMSAYMO7SDAKR","created_at":"2026-06-19T16:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"4WTWMSAY","created_at":"2026-06-19T16:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:2c978ec936ede7143e64bf6bb5ea096a9a3c15ceb2a4ff9418dc4d4a04c5e651","target":"graph","created_at":"2026-06-19T16:12:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.19531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Haitao Lin, He Zhang, Jingbo Zhang, Wenjun Zeng, Wenyao Zhang, Xiaokang Yang, Xin Jin, Yao Mu, Yuyang Zhang, Zekun Qi","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:25:28Z","title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19531","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b984d8cf8b579a999e83c24320b5257c5f1bdff2c2c47d19fbdbaeeb3371d5d","target":"record","created_at":"2026-06-19T16:12:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"14dff20fdbfd8b29e391a49c84506d79e40b88c9b6f2b5befe6d6df2f7de52ae","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:25:28Z","title_canon_sha256":"e7fe8a3a9f8f506548205193313f05dcdd0804084e79ca5380bcc18bc1bff75c"},"schema_version":"1.0","source":{"id":"2606.19531","kind":"arxiv","version":1}},"canonical_sha256":"e5a766481863bf218151241b6425169f7e6487b29102d63253d30b638b01d6af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5a766481863bf218151241b6425169f7e6487b29102d63253d30b638b01d6af","first_computed_at":"2026-06-19T16:12:27.957770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:27.957770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JbFBwzKDqQYTJjItvfaomg0BbQyihnVljm8FC6FymKz8FO8BenGmqBzlkdHPU9YcbnO94guc6759D5nV+oE+BA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:27.958120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b984d8cf8b579a999e83c24320b5257c5f1bdff2c2c47d19fbdbaeeb3371d5d","sha256:2c978ec936ede7143e64bf6bb5ea096a9a3c15ceb2a4ff9418dc4d4a04c5e651"],"state_sha256":"fd947343469f61ab95ba5bef9c0d357e5782ebef483d504dba3a33c58910198c"}