{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NUBENC25RF3LD3G72U5K4UFHU4","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":"48bf33937c8d15c7aac782f21a1ad5e74c7e4d232f4ca641801a70084fc7318c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:48:45Z","title_canon_sha256":"45dc7a26f87cd5190db22f84535396d88c15952c80e237631e7f6e4d34f507db"},"schema_version":"1.0","source":{"id":"2607.29613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29613","created_at":"2026-08-03T01:40:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29613v1","created_at":"2026-08-03T01:40:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29613","created_at":"2026-08-03T01:40:27Z"},{"alias_kind":"pith_short_12","alias_value":"NUBENC25RF3L","created_at":"2026-08-03T01:40:27Z"},{"alias_kind":"pith_short_16","alias_value":"NUBENC25RF3LD3G7","created_at":"2026-08-03T01:40:27Z"},{"alias_kind":"pith_short_8","alias_value":"NUBENC25","created_at":"2026-08-03T01:40:27Z"}],"graph_snapshots":[{"event_id":"sha256:564e60958475094f54710639cbfd76c0a40f154f3aafde17ba7d9b3e124eeacb","target":"graph","created_at":"2026-08-03T01:40:27Z","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/2607.29613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods, critic-based approaches rely on a value estimator that predominantly operates on single-frame observations or single-frame VLM backbone latents, which is a fundamental mismatch with the partially observable nature of robot control. A naive approach to incorporate observation history into the critic incurs exponential complexity with high-dimensional visual space, and still fails because pure scalar-return regression provides insufficient supervis","authors_text":"Jingjing Gong, Senyu Fei, Siyin Wang, Xianzhong Zhao, Xiaopeng Yu, Xipeng Qiu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:48:45Z","title":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29613","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":"sha256:5cdecc732c15aa012dfd233fd475f98865e541180c1d4fbc4bb60d01bf8be06a","target":"record","created_at":"2026-08-03T01:40:27Z","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":"48bf33937c8d15c7aac782f21a1ad5e74c7e4d232f4ca641801a70084fc7318c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:48:45Z","title_canon_sha256":"45dc7a26f87cd5190db22f84535396d88c15952c80e237631e7f6e4d34f507db"},"schema_version":"1.0","source":{"id":"2607.29613","kind":"arxiv","version":1}},"canonical_sha256":"6d02468b5d8976b1ecdfd53aae50a7a735ea302e38743988fe8f2a9f4992d83b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d02468b5d8976b1ecdfd53aae50a7a735ea302e38743988fe8f2a9f4992d83b","first_computed_at":"2026-08-03T01:40:27.711537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:40:27.711537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9V6iibG50oyasDPKqwUeL0v3dJH4qLg3bQRF2o9G0QoClBwbleaCGhgCAjA+rhNxXIFGL8WKUmvTCwCdgjX4Aw==","signature_status":"signed_v1","signed_at":"2026-08-03T01:40:27.713161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cdecc732c15aa012dfd233fd475f98865e541180c1d4fbc4bb60d01bf8be06a","sha256:564e60958475094f54710639cbfd76c0a40f154f3aafde17ba7d9b3e124eeacb"],"state_sha256":"882d278a7fd00e9009dfb6604690660da0cf50bd37ce2c0e0ebba1472ef8f1ee"}