{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LANUUHLOC6ANIN2FWJSBEQJ5D3","short_pith_number":"pith:LANUUHLO","canonical_record":{"source":{"id":"2501.05329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T15:55:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f34a011c42ae2291fb3ed738563f84a1dd33b4cd56cd2e232e98d35ddf2eaadf","abstract_canon_sha256":"70273d536d5d2fba7f78e00138672c20b8713659c2f7cd3a2d279c5d3f7ebf06"},"schema_version":"1.0"},"canonical_sha256":"581b4a1d6e1780d43745b26412413d1ee56534679254dc6b0cd1b2295d68e0fc","source":{"kind":"arxiv","id":"2501.05329","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LANUUHLOC6ANIN2FWJSBEQJ5D3","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T15:55:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f34a011c42ae2291fb3ed738563f84a1dd33b4cd56cd2e232e98d35ddf2eaadf","abstract_canon_sha256":"70273d536d5d2fba7f78e00138672c20b8713659c2f7cd3a2d279c5d3f7ebf06"},"schema_version":"1.0"},"canonical_sha256":"581b4a1d6e1780d43745b26412413d1ee56534679254dc6b0cd1b2295d68e0fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:04.255231Z","signature_b64":"iwPmCnGsmwKa84wJu5sWMXIkRHUEJmXPpR8ueFN//wlxGK76aWQvxr45B8nGusdww3MQs5334ePGp3j8V0gmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581b4a1d6e1780d43745b26412413d1ee56534679254dc6b0cd1b2295d68e0fc","last_reissued_at":"2026-07-05T11:31:04.254748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:04.254748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05329","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5SEWV1JdcsfcXyRcU65veCtzoaZkIjRv5PXuv4C/SbQ1e0bOZO2X/GartRa2jOqzEK0ZPcISaSG1SBuh2PWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:10:35.476211Z"},"content_sha256":"3fba63c0b19d85bda6c14dec42dfb12badec641cdbb12346d4f8af4242e2ac7b","schema_version":"1.0","event_id":"sha256:3fba63c0b19d85bda6c14dec42dfb12badec641cdbb12346d4f8af4242e2ac7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LANUUHLOC6ANIN2FWJSBEQJ5D3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dmytro Kuzmenko, Nadiya Shvai","submitted_at":"2025-01-09T15:55:08Z","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, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05329","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/2501.05329/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+NSnrMPB3f+STLaCYUCquKSziMAdWMXkumJ9FTUaVpuVq6AXnnzJzUIT9Utfd5fXa2VmYE6Hxiv4TaHkhJLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:10:35.477169Z"},"content_sha256":"304e9b76b9cb1df3d689068dc705ba5406cb19b3e171fd67c839fc4c7b5794ba","schema_version":"1.0","event_id":"sha256:304e9b76b9cb1df3d689068dc705ba5406cb19b3e171fd67c839fc4c7b5794ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/bundle.json","state_url":"https://pith.science/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T23:10:35Z","links":{"resolver":"https://pith.science/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3","bundle":"https://pith.science/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/bundle.json","state":"https://pith.science/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LANUUHLOC6ANIN2FWJSBEQJ5D3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Oy2Nq79BRYV3Sgr1Jk3f63l5FvA7mtONDaX9KMIaj1+Xx16o7uDDb2sv2yEOYQqVMklwMAu6IprPOcyxL1/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:10:35.484460Z","bundle_sha256":"25ddcf93c74500287979e290181e2fcd9a0d02562c67bba08e3049a5bb7f1f09"}}