{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BMYLTPFBPNN3WHKCV2OCVRFZTQ","short_pith_number":"pith:BMYLTPFB","schema_version":"1.0","canonical_sha256":"0b30b9bca17b5bbb1d42ae9c2ac4b99c3f3f31b03cbd1b945ab7862910ac9bbe","source":{"kind":"arxiv","id":"2606.05645","version":1},"attestation_state":"computed","paper":{"title":"Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guang Chen, Hangjun Ye, Haochen Liu, Hongwei Xie, Jianwei Cui, Jingru Wang, Jingwei Zhao, Kuiyuan Yang, Tianle Liu, Yuncheng Jiang, Zeyu Zhu, Zibin Guo, Ziyang Yao","submitted_at":"2026-06-04T03:16:31Z","abstract_excerpt":"Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, capturing correlations without explicitly modeling action-conditioned dynamics. Conversely, continuous-latent world models often lack compositional structure for causal reasoning across counterfactual futures. We introduce Discrete-WAM, a unified latent vision-action world policy that represents future visual states and ego actions as aligned discrete tokens, enabling compositional causal reasoning across alternative"},"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":"2606.05645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T03:16:31Z","cross_cats_sorted":[],"title_canon_sha256":"b2a100e6783ea83641358e3ca8a50904a30e4e75db2407d427c4951e72e1c591","abstract_canon_sha256":"dd80133828885c3fc886ba21dfa2cc814b1087eb46e809881668efb633013adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:57.844106Z","signature_b64":"t/3EXl+Gr1VNpRUPxUuCAlaEGtYh2YkGvxQYuOzKJL18EmBh7obOT3AM5+4F0slGrqYd13Vd+4Xx2YvLaFcnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b30b9bca17b5bbb1d42ae9c2ac4b99c3f3f31b03cbd1b945ab7862910ac9bbe","last_reissued_at":"2026-06-05T01:14:57.843433Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:57.843433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guang Chen, Hangjun Ye, Haochen Liu, Hongwei Xie, Jianwei Cui, Jingru Wang, Jingwei Zhao, Kuiyuan Yang, Tianle Liu, Yuncheng Jiang, Zeyu Zhu, Zibin Guo, Ziyang Yao","submitted_at":"2026-06-04T03:16:31Z","abstract_excerpt":"Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, capturing correlations without explicitly modeling action-conditioned dynamics. Conversely, continuous-latent world models often lack compositional structure for causal reasoning across counterfactual futures. We introduce Discrete-WAM, a unified latent vision-action world policy that represents future visual states and ego actions as aligned discrete tokens, enabling compositional causal reasoning across alternative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05645","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/2606.05645/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":"2606.05645","created_at":"2026-06-05T01:14:57.843523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05645v1","created_at":"2026-06-05T01:14:57.843523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05645","created_at":"2026-06-05T01:14:57.843523+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMYLTPFBPNN3","created_at":"2026-06-05T01:14:57.843523+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMYLTPFBPNN3WHKC","created_at":"2026-06-05T01:14:57.843523+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMYLTPFB","created_at":"2026-06-05T01:14:57.843523+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/BMYLTPFBPNN3WHKCV2OCVRFZTQ","json":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ.json","graph_json":"https://pith.science/api/pith-number/BMYLTPFBPNN3WHKCV2OCVRFZTQ/graph.json","events_json":"https://pith.science/api/pith-number/BMYLTPFBPNN3WHKCV2OCVRFZTQ/events.json","paper":"https://pith.science/paper/BMYLTPFB"},"agent_actions":{"view_html":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ","download_json":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ.json","view_paper":"https://pith.science/paper/BMYLTPFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05645&json=true","fetch_graph":"https://pith.science/api/pith-number/BMYLTPFBPNN3WHKCV2OCVRFZTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BMYLTPFBPNN3WHKCV2OCVRFZTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ/action/storage_attestation","attest_author":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ/action/author_attestation","sign_citation":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ/action/citation_signature","submit_replication":"https://pith.science/pith/BMYLTPFBPNN3WHKCV2OCVRFZTQ/action/replication_record"}},"created_at":"2026-06-05T01:14:57.843523+00:00","updated_at":"2026-06-05T01:14:57.843523+00:00"}