{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:55QCDR3JGY7D2HO7HQJNU2NXKI","short_pith_number":"pith:55QCDR3J","schema_version":"1.0","canonical_sha256":"ef6021c769363e3d1ddf3c12da69b75210f0d2336ec5a656e43b55178f419d94","source":{"kind":"arxiv","id":"2606.13515","version":1},"attestation_state":"computed","paper":{"title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenghao Gu, Haitao Lin, Hanyang Yu, Heng Li, Jingbo Zhang, Ping Tan, Wenyao Zhang","submitted_at":"2026-06-11T16:02:42Z","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"},"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":"2606.13515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T16:02:42Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"4bdf22ff14ba961034404c1dca328143d6b867b7e7d92e18d10eac3a4bf0538c","abstract_canon_sha256":"8c67e5bd4f6dba56de052433f075f72ef308c7da0bd1e3ea0aeafd69e947ae2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:07.831632Z","signature_b64":"V12R31XljoNJyFUEPzt7OQ0efwCIq9Cr+rMoaCwy6N8FP6NpmwrZov+hWM+ZKkbOrK4IdmVzx3OSqVDPakDGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6021c769363e3d1ddf3c12da69b75210f0d2336ec5a656e43b55178f419d94","last_reissued_at":"2026-06-12T01:10:07.830796Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:07.830796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenghao Gu, Haitao Lin, Hanyang Yu, Heng Li, Jingbo Zhang, Ping Tan, Wenyao Zhang","submitted_at":"2026-06-11T16:02:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13515","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/2606.13515/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":"2606.13515","created_at":"2026-06-12T01:10:07.830941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13515v1","created_at":"2026-06-12T01:10:07.830941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13515","created_at":"2026-06-12T01:10:07.830941+00:00"},{"alias_kind":"pith_short_12","alias_value":"55QCDR3JGY7D","created_at":"2026-06-12T01:10:07.830941+00:00"},{"alias_kind":"pith_short_16","alias_value":"55QCDR3JGY7D2HO7","created_at":"2026-06-12T01:10:07.830941+00:00"},{"alias_kind":"pith_short_8","alias_value":"55QCDR3J","created_at":"2026-06-12T01:10:07.830941+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/55QCDR3JGY7D2HO7HQJNU2NXKI","json":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI.json","graph_json":"https://pith.science/api/pith-number/55QCDR3JGY7D2HO7HQJNU2NXKI/graph.json","events_json":"https://pith.science/api/pith-number/55QCDR3JGY7D2HO7HQJNU2NXKI/events.json","paper":"https://pith.science/paper/55QCDR3J"},"agent_actions":{"view_html":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI","download_json":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI.json","view_paper":"https://pith.science/paper/55QCDR3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13515&json=true","fetch_graph":"https://pith.science/api/pith-number/55QCDR3JGY7D2HO7HQJNU2NXKI/graph.json","fetch_events":"https://pith.science/api/pith-number/55QCDR3JGY7D2HO7HQJNU2NXKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI/action/storage_attestation","attest_author":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI/action/author_attestation","sign_citation":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI/action/citation_signature","submit_replication":"https://pith.science/pith/55QCDR3JGY7D2HO7HQJNU2NXKI/action/replication_record"}},"created_at":"2026-06-12T01:10:07.830941+00:00","updated_at":"2026-06-12T01:10:07.830941+00:00"}