{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E3T6Q6SH7VAGMYXKLESUACUXUJ","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":"bf871f96011effdfe1e80d216d647e564b916d3c55303428897988849332eaa5","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T15:38:49Z","title_canon_sha256":"a77e296d40996bcd3d79b0713d3b7fc8587c532959ebe53ae0d7a58f2809c21b"},"schema_version":"1.0","source":{"id":"2507.01823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01823","created_at":"2026-07-05T11:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01823v1","created_at":"2026-07-05T11:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01823","created_at":"2026-07-05T11:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"E3T6Q6SH7VAG","created_at":"2026-07-05T11:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"E3T6Q6SH7VAGMYXK","created_at":"2026-07-05T11:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"E3T6Q6SH","created_at":"2026-07-05T11:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:03289e03019a30931a84b84d8395741b19954a923d98593cf9c300fd90b48de8","target":"graph","created_at":"2026-07-05T11:30:55Z","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/2507.01823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained environments. Our method efficiently distills a high-capacity multi-task agent (317M parameters) into a compact model (1M parameters) on the MT30 benchmark, significantly improving performance across diverse tasks. Our distilled model achieves a state-of-the-art normalized score of 28.45, surpassing the original 1M parameter model score of 18.93. This improvement demonstrates the ability of our distillation technique ","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":"2025-07-02T15:38:49Z","title":"TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01823","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:e4d753a9ddfd432514feec6d797c8e0e30101dc84375548c7d36a04526600e0a","target":"record","created_at":"2026-07-05T11:30:55Z","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":"bf871f96011effdfe1e80d216d647e564b916d3c55303428897988849332eaa5","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T15:38:49Z","title_canon_sha256":"a77e296d40996bcd3d79b0713d3b7fc8587c532959ebe53ae0d7a58f2809c21b"},"schema_version":"1.0","source":{"id":"2507.01823","kind":"arxiv","version":1}},"canonical_sha256":"26e7e87a47fd406662ea5925400a97a27140fc001abd3b706cd46334c019644a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26e7e87a47fd406662ea5925400a97a27140fc001abd3b706cd46334c019644a","first_computed_at":"2026-07-05T11:30:55.917276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:55.917276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OF/ocd0ns4M6xuCj47ilxo4I+ganXDmeDDvi/TGkvD5gS7GmyiatydCNAsUEX6lKpN6ihFUOSdaN1GoxF9uFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:55.918035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d753a9ddfd432514feec6d797c8e0e30101dc84375548c7d36a04526600e0a","sha256:03289e03019a30931a84b84d8395741b19954a923d98593cf9c300fd90b48de8"],"state_sha256":"20a6709396301a22c8176fa1cc704b3d11a343cd0f844b8c7bccd94ba7aa725c"}