{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BLTRYIPYGPD7BAKMHWTZ35MDLR","short_pith_number":"pith:BLTRYIPY","schema_version":"1.0","canonical_sha256":"0ae71c21f833c7f0814c3da79df5835c509f672e573efc06936a52aeda6e2854","source":{"kind":"arxiv","id":"2606.27504","version":1},"attestation_state":"computed","paper":{"title":"ReWorld: Learning Better Representations for World Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Guang Chen, Haiyang Sun, Hangjun Ye, Jingfeng Yao, Kaixin Xiong, Lijun Zhou, Tianze Xia, Wenyu Liu, Xinggang Wang, Yu Zhu, Zhenxin Zhu","submitted_at":"2026-06-25T19:37:58Z","abstract_excerpt":"World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus largely on model architecture design, and how a WAM can efficiently learn better world representations for planning remains underexplored. To address this gap, we propose ReWorld, the first representation learning framework specifically designed for autonomous-driving world action models. In WAMs, standard training supervises only the output ends of the generation and planning modules, leaving the intermediate represent"},"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":"2606.27504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T19:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"b07b18ba2f0e88d553c8fed76065f35ea41e64844abadf7d7834937fa59150af","abstract_canon_sha256":"83c5c791c08f8bd98adf9a294e93c959b9132d30906ed12e6d4d13a043269f76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:08.485208Z","signature_b64":"arTzXeIWYfVLzUiG1CwP8UIEAQLW2VLH5geXQmVJmapU+AA5tv4w4eM8TbDyrTXLwV2bz6X7sK3DqVUoCPaIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ae71c21f833c7f0814c3da79df5835c509f672e573efc06936a52aeda6e2854","last_reissued_at":"2026-06-29T00:14:08.484811Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:08.484811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReWorld: Learning Better Representations for World Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Guang Chen, Haiyang Sun, Hangjun Ye, Jingfeng Yao, Kaixin Xiong, Lijun Zhou, Tianze Xia, Wenyu Liu, Xinggang Wang, Yu Zhu, Zhenxin Zhu","submitted_at":"2026-06-25T19:37:58Z","abstract_excerpt":"World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus largely on model architecture design, and how a WAM can efficiently learn better world representations for planning remains underexplored. To address this gap, we propose ReWorld, the first representation learning framework specifically designed for autonomous-driving world action models. In WAMs, standard training supervises only the output ends of the generation and planning modules, leaving the intermediate represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27504","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/2606.27504/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":"2606.27504","created_at":"2026-06-29T00:14:08.484866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27504v1","created_at":"2026-06-29T00:14:08.484866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27504","created_at":"2026-06-29T00:14:08.484866+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLTRYIPYGPD7","created_at":"2026-06-29T00:14:08.484866+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLTRYIPYGPD7BAKM","created_at":"2026-06-29T00:14:08.484866+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLTRYIPY","created_at":"2026-06-29T00:14:08.484866+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/BLTRYIPYGPD7BAKMHWTZ35MDLR","json":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR.json","graph_json":"https://pith.science/api/pith-number/BLTRYIPYGPD7BAKMHWTZ35MDLR/graph.json","events_json":"https://pith.science/api/pith-number/BLTRYIPYGPD7BAKMHWTZ35MDLR/events.json","paper":"https://pith.science/paper/BLTRYIPY"},"agent_actions":{"view_html":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR","download_json":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR.json","view_paper":"https://pith.science/paper/BLTRYIPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27504&json=true","fetch_graph":"https://pith.science/api/pith-number/BLTRYIPYGPD7BAKMHWTZ35MDLR/graph.json","fetch_events":"https://pith.science/api/pith-number/BLTRYIPYGPD7BAKMHWTZ35MDLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR/action/storage_attestation","attest_author":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR/action/author_attestation","sign_citation":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR/action/citation_signature","submit_replication":"https://pith.science/pith/BLTRYIPYGPD7BAKMHWTZ35MDLR/action/replication_record"}},"created_at":"2026-06-29T00:14:08.484866+00:00","updated_at":"2026-06-29T00:14:08.484866+00:00"}