{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUBENC25RF3LD3G72U5K4UFHU4","short_pith_number":"pith:NUBENC25","schema_version":"1.0","canonical_sha256":"6d02468b5d8976b1ecdfd53aae50a7a735ea302e38743988fe8f2a9f4992d83b","source":{"kind":"arxiv","id":"2607.29613","version":1},"attestation_state":"computed","paper":{"title":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Jingjing Gong, Senyu Fei, Siyin Wang, Xianzhong Zhao, Xiaopeng Yu, Xipeng Qiu","submitted_at":"2026-07-31T16:48:45Z","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"},"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":"2607.29613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:48:45Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"45dc7a26f87cd5190db22f84535396d88c15952c80e237631e7f6e4d34f507db","abstract_canon_sha256":"48bf33937c8d15c7aac782f21a1ad5e74c7e4d232f4ca641801a70084fc7318c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:40:27.713161Z","signature_b64":"9V6iibG50oyasDPKqwUeL0v3dJH4qLg3bQRF2o9G0QoClBwbleaCGhgCAjA+rhNxXIFGL8WKUmvTCwCdgjX4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d02468b5d8976b1ecdfd53aae50a7a735ea302e38743988fe8f2a9f4992d83b","last_reissued_at":"2026-08-03T01:40:27.711537Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:40:27.711537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Jingjing Gong, Senyu Fei, Siyin Wang, Xianzhong Zhao, Xiaopeng Yu, Xipeng Qiu","submitted_at":"2026-07-31T16:48:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29613","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/2607.29613/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":"2607.29613","created_at":"2026-08-03T01:40:27.712492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29613v1","created_at":"2026-08-03T01:40:27.712492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29613","created_at":"2026-08-03T01:40:27.712492+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUBENC25RF3L","created_at":"2026-08-03T01:40:27.712492+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUBENC25RF3LD3G7","created_at":"2026-08-03T01:40:27.712492+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUBENC25","created_at":"2026-08-03T01:40:27.712492+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/NUBENC25RF3LD3G72U5K4UFHU4","json":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4.json","graph_json":"https://pith.science/api/pith-number/NUBENC25RF3LD3G72U5K4UFHU4/graph.json","events_json":"https://pith.science/api/pith-number/NUBENC25RF3LD3G72U5K4UFHU4/events.json","paper":"https://pith.science/paper/NUBENC25"},"agent_actions":{"view_html":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4","download_json":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4.json","view_paper":"https://pith.science/paper/NUBENC25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29613&json=true","fetch_graph":"https://pith.science/api/pith-number/NUBENC25RF3LD3G72U5K4UFHU4/graph.json","fetch_events":"https://pith.science/api/pith-number/NUBENC25RF3LD3G72U5K4UFHU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4/action/storage_attestation","attest_author":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4/action/author_attestation","sign_citation":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4/action/citation_signature","submit_replication":"https://pith.science/pith/NUBENC25RF3LD3G72U5K4UFHU4/action/replication_record"}},"created_at":"2026-08-03T01:40:27.712492+00:00","updated_at":"2026-08-03T01:40:27.712492+00:00"}