{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M2PYITSCIBLYFI4ANSI6NEILOI","short_pith_number":"pith:M2PYITSC","schema_version":"1.0","canonical_sha256":"669f844e42405782a3806c91e6910b720d896675d9f8af4e04adf89abb296b14","source":{"kind":"arxiv","id":"2606.03201","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"He Liu, Jacob E. Kooi, Kevin Sebastian Luck, Shujian Yu, Thomas Delliaux, Vincent Fran\\c{c}ois-Lavet, Xinrui Zu, Zhao Yang","submitted_at":"2026-06-02T06:00:15Z","abstract_excerpt":"Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of domain gaps. We introduce XIPER (Cross-domain Video Prediction Reward), a reward model for learning from expert videos collected in a visually different domain, where the agent's appearance differs due to factors such as color, morphology, or the sim-to-real gap. More specifically, XIPER trains a cross-domain video prediction model that maps agent observations into the expert domain and uses the prediction likelihood as a reward signal. Experiments "},"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":"2606.03201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T06:00:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae31d745c0c22e85b8fd215bd058a5f907770d959492ac6886c790d28f0c35e9","abstract_canon_sha256":"f120c3966a09d21ad62d35c7e385e9b84ec70e1ebba0fa1c42cda6a68b4ce12e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:34.737312Z","signature_b64":"tsaUf36TXM//ql2N1s0ccGyPO8gXjnvYDeJjCPG7Q/0D/fkfF4XI8g3f7dCUEtYDS6KDUlWao9ObOZGkFWlCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669f844e42405782a3806c91e6910b720d896675d9f8af4e04adf89abb296b14","last_reissued_at":"2026-06-03T01:05:34.736907Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:34.736907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"He Liu, Jacob E. Kooi, Kevin Sebastian Luck, Shujian Yu, Thomas Delliaux, Vincent Fran\\c{c}ois-Lavet, Xinrui Zu, Zhao Yang","submitted_at":"2026-06-02T06:00:15Z","abstract_excerpt":"Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of domain gaps. We introduce XIPER (Cross-domain Video Prediction Reward), a reward model for learning from expert videos collected in a visually different domain, where the agent's appearance differs due to factors such as color, morphology, or the sim-to-real gap. More specifically, XIPER trains a cross-domain video prediction model that maps agent observations into the expert domain and uses the prediction likelihood as a reward signal. Experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03201","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/2606.03201/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":"2606.03201","created_at":"2026-06-03T01:05:34.736968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03201v1","created_at":"2026-06-03T01:05:34.736968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03201","created_at":"2026-06-03T01:05:34.736968+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2PYITSCIBLY","created_at":"2026-06-03T01:05:34.736968+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2PYITSCIBLYFI4A","created_at":"2026-06-03T01:05:34.736968+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2PYITSC","created_at":"2026-06-03T01:05:34.736968+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/M2PYITSCIBLYFI4ANSI6NEILOI","json":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI.json","graph_json":"https://pith.science/api/pith-number/M2PYITSCIBLYFI4ANSI6NEILOI/graph.json","events_json":"https://pith.science/api/pith-number/M2PYITSCIBLYFI4ANSI6NEILOI/events.json","paper":"https://pith.science/paper/M2PYITSC"},"agent_actions":{"view_html":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI","download_json":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI.json","view_paper":"https://pith.science/paper/M2PYITSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03201&json=true","fetch_graph":"https://pith.science/api/pith-number/M2PYITSCIBLYFI4ANSI6NEILOI/graph.json","fetch_events":"https://pith.science/api/pith-number/M2PYITSCIBLYFI4ANSI6NEILOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI/action/storage_attestation","attest_author":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI/action/author_attestation","sign_citation":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI/action/citation_signature","submit_replication":"https://pith.science/pith/M2PYITSCIBLYFI4ANSI6NEILOI/action/replication_record"}},"created_at":"2026-06-03T01:05:34.736968+00:00","updated_at":"2026-06-03T01:05:34.736968+00:00"}