{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4EVPZINANAX3WOCMQNPVWIKW26","short_pith_number":"pith:4EVPZINA","schema_version":"1.0","canonical_sha256":"e12afca1a0682fbb384c835f5b2156d796acc6d5583bcbe5f0ccb3482e45ac5d","source":{"kind":"arxiv","id":"2606.17906","version":1},"attestation_state":"computed","paper":{"title":"WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haozhan Li, Shanghang Zhang, Xiaowei Chi, Yu Qi, Zezhong Qian, Zhi Yang Chen","submitted_at":"2026-06-16T13:29:12Z","abstract_excerpt":"Recent World-Action (WA) models demonstrate strong generalization ability and data efficiency, but they typically rely on expert trajectories for training. This reliance limits their ability to acquire fine-grained manipulation skills beyond the demonstration distribution and prevents them from continuously improving through real-world interaction. To address these limitations, we propose WAM-RL, a reinforcement learning framework that enables joint optimization of the world model and the action model through online interaction with the environment. By allowing the two components to co-evolve,"},"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":"2606.17906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:29:12Z","cross_cats_sorted":[],"title_canon_sha256":"c414a336815b7043cf4c37de5bc2b5f3efd6b6afa21d74803d02a726fa6db021","abstract_canon_sha256":"b7080708b719b062f2516d70d317b2c70bad7e0944e2c76010be7626a686cfea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:43.293065Z","signature_b64":"cUMpUFbD7MbUGTA69T4M+uRu0lQyOi9xe37Is5slj9Tkee3MeYM7865vF4aMdAyhtsI5OX9TqpBe2HpRHUD1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e12afca1a0682fbb384c835f5b2156d796acc6d5583bcbe5f0ccb3482e45ac5d","last_reissued_at":"2026-06-19T16:10:43.292683Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:43.292683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haozhan Li, Shanghang Zhang, Xiaowei Chi, Yu Qi, Zezhong Qian, Zhi Yang Chen","submitted_at":"2026-06-16T13:29:12Z","abstract_excerpt":"Recent World-Action (WA) models demonstrate strong generalization ability and data efficiency, but they typically rely on expert trajectories for training. This reliance limits their ability to acquire fine-grained manipulation skills beyond the demonstration distribution and prevents them from continuously improving through real-world interaction. To address these limitations, we propose WAM-RL, a reinforcement learning framework that enables joint optimization of the world model and the action model through online interaction with the environment. By allowing the two components to co-evolve,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17906","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/2606.17906/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":"2606.17906","created_at":"2026-06-19T16:10:43.292744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17906v1","created_at":"2026-06-19T16:10:43.292744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17906","created_at":"2026-06-19T16:10:43.292744+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EVPZINANAX3","created_at":"2026-06-19T16:10:43.292744+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EVPZINANAX3WOCM","created_at":"2026-06-19T16:10:43.292744+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EVPZINA","created_at":"2026-06-19T16:10:43.292744+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/4EVPZINANAX3WOCMQNPVWIKW26","json":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26.json","graph_json":"https://pith.science/api/pith-number/4EVPZINANAX3WOCMQNPVWIKW26/graph.json","events_json":"https://pith.science/api/pith-number/4EVPZINANAX3WOCMQNPVWIKW26/events.json","paper":"https://pith.science/paper/4EVPZINA"},"agent_actions":{"view_html":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26","download_json":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26.json","view_paper":"https://pith.science/paper/4EVPZINA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17906&json=true","fetch_graph":"https://pith.science/api/pith-number/4EVPZINANAX3WOCMQNPVWIKW26/graph.json","fetch_events":"https://pith.science/api/pith-number/4EVPZINANAX3WOCMQNPVWIKW26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26/action/storage_attestation","attest_author":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26/action/author_attestation","sign_citation":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26/action/citation_signature","submit_replication":"https://pith.science/pith/4EVPZINANAX3WOCMQNPVWIKW26/action/replication_record"}},"created_at":"2026-06-19T16:10:43.292744+00:00","updated_at":"2026-06-19T16:10:43.292744+00:00"}