{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOEKMESG77HHBKHSQEQPT4CJJE","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":"5a095da9b9963c1f22983ac8868940d723074deadafd1d814808ac42cf08191b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T17:59:43Z","title_canon_sha256":"1b7914d5818a1676bcbc949c3c8d69a1465914bc8c3980a571f7884201508755"},"schema_version":"1.0","source":{"id":"2606.13674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13674","created_at":"2026-06-12T01:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13674v1","created_at":"2026-06-12T01:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13674","created_at":"2026-06-12T01:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"OOEKMESG77HH","created_at":"2026-06-12T01:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"OOEKMESG77HHBKHS","created_at":"2026-06-12T01:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"OOEKMESG","created_at":"2026-06-12T01:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:da25c090b337ab7f52235fe14ede2507fa23ab9e176deb2a815a3a69ae93091d","target":"graph","created_at":"2026-06-12T01:10:22Z","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/2606.13674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junke Wang, Qihang Zhang, Shuai Yang, Yiming Luo, Yinghao Xu, Yu-Gang Jiang, Yujun Shen, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T17:59:43Z","title":"RepWAM: World Action Modeling with Representation Visual-Action Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13674","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:c15d67b0e6a0f9397e51bffa31193a1153b0cdfaa2b9ca62b866a42b20be3c8f","target":"record","created_at":"2026-06-12T01:10:22Z","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":"5a095da9b9963c1f22983ac8868940d723074deadafd1d814808ac42cf08191b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T17:59:43Z","title_canon_sha256":"1b7914d5818a1676bcbc949c3c8d69a1465914bc8c3980a571f7884201508755"},"schema_version":"1.0","source":{"id":"2606.13674","kind":"arxiv","version":1}},"canonical_sha256":"7388a61246ffce70a8f28120f9f0494906b3372c6c455b018d62ed160746bb4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7388a61246ffce70a8f28120f9f0494906b3372c6c455b018d62ed160746bb4a","first_computed_at":"2026-06-12T01:10:22.821580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:22.821580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pwZ1amr9FbzdITPUzdm+Q0prc2EpE5v++DriXXerwxvdPzMwjB9NzWWZboZNHNwjwFdzqIIFbIUY4LMpzjHqBw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:22.822281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c15d67b0e6a0f9397e51bffa31193a1153b0cdfaa2b9ca62b866a42b20be3c8f","sha256:da25c090b337ab7f52235fe14ede2507fa23ab9e176deb2a815a3a69ae93091d"],"state_sha256":"489c34d76bea6264c275501cf292eac656dab1c83521c2ffb7c44e8e16c7b59c"}