{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OOEKMESG77HHBKHSQEQPT4CJJE","short_pith_number":"pith:OOEKMESG","schema_version":"1.0","canonical_sha256":"7388a61246ffce70a8f28120f9f0494906b3372c6c455b018d62ed160746bb4a","source":{"kind":"arxiv","id":"2606.13674","version":1},"attestation_state":"computed","paper":{"title":"RepWAM: World Action Modeling with Representation Visual-Action Tokenizers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junke Wang, Qihang Zhang, Shuai Yang, Yiming Luo, Yinghao Xu, Yu-Gang Jiang, Yujun Shen, Zuxuan Wu","submitted_at":"2026-06-11T17:59:43Z","abstract_excerpt":"This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-oriented video tokenizers from pretrained video generation models. Although these tokenizers preserve visual fidelity, pixel reconstruction alone provides limited guidance for learning instruction-following dynamics that connect future prediction with robot control. To address this, we explore a semantic visual-action latent space for representation-centric world action modeling. Specifically, we train a representation vis"},"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":"2606.13674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"1b7914d5818a1676bcbc949c3c8d69a1465914bc8c3980a571f7884201508755","abstract_canon_sha256":"5a095da9b9963c1f22983ac8868940d723074deadafd1d814808ac42cf08191b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:22.822281Z","signature_b64":"pwZ1amr9FbzdITPUzdm+Q0prc2EpE5v++DriXXerwxvdPzMwjB9NzWWZboZNHNwjwFdzqIIFbIUY4LMpzjHqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7388a61246ffce70a8f28120f9f0494906b3372c6c455b018d62ed160746bb4a","last_reissued_at":"2026-06-12T01:10:22.821580Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:22.821580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepWAM: World Action Modeling with Representation Visual-Action Tokenizers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junke Wang, Qihang Zhang, Shuai Yang, Yiming Luo, Yinghao Xu, Yu-Gang Jiang, Yujun Shen, Zuxuan Wu","submitted_at":"2026-06-11T17:59:43Z","abstract_excerpt":"This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-oriented video tokenizers from pretrained video generation models. Although these tokenizers preserve visual fidelity, pixel reconstruction alone provides limited guidance for learning instruction-following dynamics that connect future prediction with robot control. To address this, we explore a semantic visual-action latent space for representation-centric world action modeling. Specifically, we train a representation vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13674","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/2606.13674/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":"2606.13674","created_at":"2026-06-12T01:10:22.821696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13674v1","created_at":"2026-06-12T01:10:22.821696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13674","created_at":"2026-06-12T01:10:22.821696+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOEKMESG77HH","created_at":"2026-06-12T01:10:22.821696+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOEKMESG77HHBKHS","created_at":"2026-06-12T01:10:22.821696+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOEKMESG","created_at":"2026-06-12T01:10:22.821696+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/OOEKMESG77HHBKHSQEQPT4CJJE","json":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE.json","graph_json":"https://pith.science/api/pith-number/OOEKMESG77HHBKHSQEQPT4CJJE/graph.json","events_json":"https://pith.science/api/pith-number/OOEKMESG77HHBKHSQEQPT4CJJE/events.json","paper":"https://pith.science/paper/OOEKMESG"},"agent_actions":{"view_html":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE","download_json":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE.json","view_paper":"https://pith.science/paper/OOEKMESG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13674&json=true","fetch_graph":"https://pith.science/api/pith-number/OOEKMESG77HHBKHSQEQPT4CJJE/graph.json","fetch_events":"https://pith.science/api/pith-number/OOEKMESG77HHBKHSQEQPT4CJJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE/action/storage_attestation","attest_author":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE/action/author_attestation","sign_citation":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE/action/citation_signature","submit_replication":"https://pith.science/pith/OOEKMESG77HHBKHSQEQPT4CJJE/action/replication_record"}},"created_at":"2026-06-12T01:10:22.821696+00:00","updated_at":"2026-06-12T01:10:22.821696+00:00"}