{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LANUUHLOC6ANIN2FWJSBEQJ5D3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"70273d536d5d2fba7f78e00138672c20b8713659c2f7cd3a2d279c5d3f7ebf06","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T15:55:08Z","title_canon_sha256":"f34a011c42ae2291fb3ed738563f84a1dd33b4cd56cd2e232e98d35ddf2eaadf"},"schema_version":"1.0","source":{"id":"2501.05329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05329","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05329v1","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05329","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"LANUUHLOC6AN","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"LANUUHLOC6ANIN2F","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"LANUUHLO","created_at":"2026-07-05T11:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:304e9b76b9cb1df3d689068dc705ba5406cb19b3e171fd67c839fc4c7b5794ba","target":"graph","created_at":"2026-07-05T11:31:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.05329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent (317M parameters) into a compact 1M parameter model, achieving state-of-the-art performance on the MT30 benchmark with a normalized score of 28.45, a substantial improvement over the original 1M parameter model's score of 18.93. This demonstrates the ability of our distillation technique to consolidate complex multi-task knowledge effectively. Additionally, ","authors_text":"Dmytro Kuzmenko, Nadiya Shvai","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T15:55:08Z","title":"Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05329","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3fba63c0b19d85bda6c14dec42dfb12badec641cdbb12346d4f8af4242e2ac7b","target":"record","created_at":"2026-07-05T11:31:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"70273d536d5d2fba7f78e00138672c20b8713659c2f7cd3a2d279c5d3f7ebf06","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T15:55:08Z","title_canon_sha256":"f34a011c42ae2291fb3ed738563f84a1dd33b4cd56cd2e232e98d35ddf2eaadf"},"schema_version":"1.0","source":{"id":"2501.05329","kind":"arxiv","version":1}},"canonical_sha256":"581b4a1d6e1780d43745b26412413d1ee56534679254dc6b0cd1b2295d68e0fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"581b4a1d6e1780d43745b26412413d1ee56534679254dc6b0cd1b2295d68e0fc","first_computed_at":"2026-07-05T11:31:04.254748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:04.254748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwPmCnGsmwKa84wJu5sWMXIkRHUEJmXPpR8ueFN//wlxGK76aWQvxr45B8nGusdww3MQs5334ePGp3j8V0gmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:04.255231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fba63c0b19d85bda6c14dec42dfb12badec641cdbb12346d4f8af4242e2ac7b","sha256:304e9b76b9cb1df3d689068dc705ba5406cb19b3e171fd67c839fc4c7b5794ba"],"state_sha256":"4876aaeb4aeca4b9fceaa74db2610320e4752aa5d9c3f4285b0280124b9ddc87"}