{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5YLMPHVJOVIB2Z2UAZE2QAP4AR","short_pith_number":"pith:5YLMPHVJ","schema_version":"1.0","canonical_sha256":"ee16c79ea975501d67540649a801fc044fc681976983a05f516c490c06bbb0c0","source":{"kind":"arxiv","id":"2407.13466","version":1},"attestation_state":"computed","paper":{"title":"LIMT: Language-Informed Multi-Task Visual World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Elie Aljalbout, Maximilian Karl, Nikolaos Sotirakis, Nutan Chen, Patrick van der Smagt","submitted_at":"2024-07-18T12:40:58Z","abstract_excerpt":"Most recent successes in robot reinforcement learning involve learning a specialized single-task agent.\n  However, robots capable of performing multiple tasks can be much more valuable in real-world applications.\n  Multi-task reinforcement learning can be very challenging due to the increased sample complexity and the potentially conflicting task objectives.\n  Previous work on this topic is dominated by model-free approaches.\n  The latter can be very sample inefficient even when learning specialized single-task agents.\n  In this work, we focus on model-based multi-task reinforcement learning.\n"},"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":"2407.13466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-18T12:40:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53317d8f0ffd1e59de8c47e1dc8393397889771208742faf8ff278d2e960d6de","abstract_canon_sha256":"70c1c148a9c2a0d00fb7e88104083af641e9f2f19c409654d1faf81d27aaeabf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:39.349733Z","signature_b64":"FkfxhKMEJXNDQivPNzMGqhH3pqTmJDaJqfNHvkCAL/bLBaPS/hm2GWF39mR8c0jX9gO6gI6xzb4NmhlPkw12Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee16c79ea975501d67540649a801fc044fc681976983a05f516c490c06bbb0c0","last_reissued_at":"2026-07-05T08:45:39.349341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:39.349341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIMT: Language-Informed Multi-Task Visual World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Elie Aljalbout, Maximilian Karl, Nikolaos Sotirakis, Nutan Chen, Patrick van der Smagt","submitted_at":"2024-07-18T12:40:58Z","abstract_excerpt":"Most recent successes in robot reinforcement learning involve learning a specialized single-task agent.\n  However, robots capable of performing multiple tasks can be much more valuable in real-world applications.\n  Multi-task reinforcement learning can be very challenging due to the increased sample complexity and the potentially conflicting task objectives.\n  Previous work on this topic is dominated by model-free approaches.\n  The latter can be very sample inefficient even when learning specialized single-task agents.\n  In this work, we focus on model-based multi-task reinforcement learning.\n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13466","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/2407.13466/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":"2407.13466","created_at":"2026-07-05T08:45:39.349407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13466v1","created_at":"2026-07-05T08:45:39.349407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13466","created_at":"2026-07-05T08:45:39.349407+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YLMPHVJOVIB","created_at":"2026-07-05T08:45:39.349407+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YLMPHVJOVIB2Z2U","created_at":"2026-07-05T08:45:39.349407+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YLMPHVJ","created_at":"2026-07-05T08:45:39.349407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12442","citing_title":"Multi-Task Reinforcement Learning for Quadrotors","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR","json":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR.json","graph_json":"https://pith.science/api/pith-number/5YLMPHVJOVIB2Z2UAZE2QAP4AR/graph.json","events_json":"https://pith.science/api/pith-number/5YLMPHVJOVIB2Z2UAZE2QAP4AR/events.json","paper":"https://pith.science/paper/5YLMPHVJ"},"agent_actions":{"view_html":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR","download_json":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR.json","view_paper":"https://pith.science/paper/5YLMPHVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13466&json=true","fetch_graph":"https://pith.science/api/pith-number/5YLMPHVJOVIB2Z2UAZE2QAP4AR/graph.json","fetch_events":"https://pith.science/api/pith-number/5YLMPHVJOVIB2Z2UAZE2QAP4AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR/action/storage_attestation","attest_author":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR/action/author_attestation","sign_citation":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR/action/citation_signature","submit_replication":"https://pith.science/pith/5YLMPHVJOVIB2Z2UAZE2QAP4AR/action/replication_record"}},"created_at":"2026-07-05T08:45:39.349407+00:00","updated_at":"2026-07-05T08:45:39.349407+00:00"}