{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:55QCDR3JGY7D2HO7HQJNU2NXKI","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":"8c67e5bd4f6dba56de052433f075f72ef308c7da0bd1e3ea0aeafd69e947ae2f","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T16:02:42Z","title_canon_sha256":"4bdf22ff14ba961034404c1dca328143d6b867b7e7d92e18d10eac3a4bf0538c"},"schema_version":"1.0","source":{"id":"2606.13515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13515","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13515v1","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13515","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"55QCDR3JGY7D","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"55QCDR3JGY7D2HO7","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"55QCDR3J","created_at":"2026-06-12T01:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:d7200ee4166aecf354571af4180703c3594212345e64e46c3a6c363efc695789","target":"graph","created_at":"2026-06-12T01:10:07Z","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/2606.13515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World Action Models (WAMs) present a promising paradigm for robotic control via video prediction. However, current WAMs suffer from fundamental spatial bottlenecks: standard text inputs introduce referential ambiguity in cluttered scenes, while unstructured RGB predictions lack semantic grounding and remain biased by task-irrelevant backgrounds. To overcome these limitations, we introduce MaskWAM, an object-centric world-action model. By jointly integrating masks as both explicit inputs and predictions via a unified Mixture of Transformers (MoT), MaskWAM unlocks robust policy generalization. T","authors_text":"Chenghao Gu, Haitao Lin, Hanyang Yu, Heng Li, Jingbo Zhang, Ping Tan, Wenyao Zhang","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T16:02:42Z","title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13515","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":"sha256:06f5db465c127da195bfacc5a71f522cbfdce35b7c46cffeb6643b81cc79d8c2","target":"record","created_at":"2026-06-12T01:10:07Z","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":"8c67e5bd4f6dba56de052433f075f72ef308c7da0bd1e3ea0aeafd69e947ae2f","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T16:02:42Z","title_canon_sha256":"4bdf22ff14ba961034404c1dca328143d6b867b7e7d92e18d10eac3a4bf0538c"},"schema_version":"1.0","source":{"id":"2606.13515","kind":"arxiv","version":1}},"canonical_sha256":"ef6021c769363e3d1ddf3c12da69b75210f0d2336ec5a656e43b55178f419d94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef6021c769363e3d1ddf3c12da69b75210f0d2336ec5a656e43b55178f419d94","first_computed_at":"2026-06-12T01:10:07.830796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:07.830796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V12R31XljoNJyFUEPzt7OQ0efwCIq9Cr+rMoaCwy6N8FP6NpmwrZov+hWM+ZKkbOrK4IdmVzx3OSqVDPakDGCA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:07.831632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06f5db465c127da195bfacc5a71f522cbfdce35b7c46cffeb6643b81cc79d8c2","sha256:d7200ee4166aecf354571af4180703c3594212345e64e46c3a6c363efc695789"],"state_sha256":"e2cde5935f9abd0e738673fb5f094c6b23a0403b035f8152f19237cd6d6f2e62"}