{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GVNCXMYHHHGV6IMN4TPU45YO46","short_pith_number":"pith:GVNCXMYH","schema_version":"1.0","canonical_sha256":"355a2bb30739cd5f218de4df4e770ee7875c1383c63e3f243f53ee4e7bc64328","source":{"kind":"arxiv","id":"2607.16602","version":1},"attestation_state":"computed","paper":{"title":"PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fenjiao Cheng, Han Wang, Roy Ka-Wei Lee, Rui Cao, Shuoshuo Xue, Xiaodang Liang, Zijun Wang","submitted_at":"2026-07-18T02:42:27Z","abstract_excerpt":"Action-conditioned world models are a key component of embodied AI, serving as scalable policy evaluators that reduce reliance on expensive real-world rollouts. To accurately capture diverse action-induced dynamics, such models should satisfy three key objectives-Physical Plausibility (P), Action Adherence (A), and Visual Fidelity (V), collectively referred to as PAV-while remaining robust to both in-distribution (ID) expert demonstrations and out-of-distribution (OOD) actions. However, existing methods primarily rely on ID action-video pairs and pixel-level reconstruction losses, which do not"},"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":"2607.16602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-18T02:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"d11e80ef4d63a5c3b09355da03bdf48d04cc899817caa3b8f90c84a97e1da4c3","abstract_canon_sha256":"6f3adc80cc3b79934b94776adeb3554858ee677b64f93867c41d409b2c529692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:27.722941Z","signature_b64":"6hlJpXeznMECgNLAQysSZo0M4HpYFbc19U3/Ws3NJADcTxK/tIOswteilolzM2pjkI263xI0bYxpPIyAT5fQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355a2bb30739cd5f218de4df4e770ee7875c1383c63e3f243f53ee4e7bc64328","last_reissued_at":"2026-07-21T00:20:27.722051Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:27.722051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fenjiao Cheng, Han Wang, Roy Ka-Wei Lee, Rui Cao, Shuoshuo Xue, Xiaodang Liang, Zijun Wang","submitted_at":"2026-07-18T02:42:27Z","abstract_excerpt":"Action-conditioned world models are a key component of embodied AI, serving as scalable policy evaluators that reduce reliance on expensive real-world rollouts. To accurately capture diverse action-induced dynamics, such models should satisfy three key objectives-Physical Plausibility (P), Action Adherence (A), and Visual Fidelity (V), collectively referred to as PAV-while remaining robust to both in-distribution (ID) expert demonstrations and out-of-distribution (OOD) actions. However, existing methods primarily rely on ID action-video pairs and pixel-level reconstruction losses, which do not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16602","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/2607.16602/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":"2607.16602","created_at":"2026-07-21T00:20:27.722516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16602v1","created_at":"2026-07-21T00:20:27.722516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16602","created_at":"2026-07-21T00:20:27.722516+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVNCXMYHHHGV","created_at":"2026-07-21T00:20:27.722516+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVNCXMYHHHGV6IMN","created_at":"2026-07-21T00:20:27.722516+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVNCXMYH","created_at":"2026-07-21T00:20:27.722516+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/GVNCXMYHHHGV6IMN4TPU45YO46","json":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46.json","graph_json":"https://pith.science/api/pith-number/GVNCXMYHHHGV6IMN4TPU45YO46/graph.json","events_json":"https://pith.science/api/pith-number/GVNCXMYHHHGV6IMN4TPU45YO46/events.json","paper":"https://pith.science/paper/GVNCXMYH"},"agent_actions":{"view_html":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46","download_json":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46.json","view_paper":"https://pith.science/paper/GVNCXMYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16602&json=true","fetch_graph":"https://pith.science/api/pith-number/GVNCXMYHHHGV6IMN4TPU45YO46/graph.json","fetch_events":"https://pith.science/api/pith-number/GVNCXMYHHHGV6IMN4TPU45YO46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46/action/storage_attestation","attest_author":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46/action/author_attestation","sign_citation":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46/action/citation_signature","submit_replication":"https://pith.science/pith/GVNCXMYHHHGV6IMN4TPU45YO46/action/replication_record"}},"created_at":"2026-07-21T00:20:27.722516+00:00","updated_at":"2026-07-21T00:20:27.722516+00:00"}