{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MBW3LIJ5GYXQBUZJKTORKI7BVF","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":"8f892230db0242756ddbbc82572ff43b185997ee966e0832aeb213e42dbf64cf","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T21:39:01Z","title_canon_sha256":"18bb3269119cd5dd99c626764b993459cbc4b7bcf564d4f00a96c7c68e254c61"},"schema_version":"1.0","source":{"id":"2506.21782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21782","created_at":"2026-07-05T11:28:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21782v1","created_at":"2026-07-05T11:28:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21782","created_at":"2026-07-05T11:28:00Z"},{"alias_kind":"pith_short_12","alias_value":"MBW3LIJ5GYXQ","created_at":"2026-07-05T11:28:00Z"},{"alias_kind":"pith_short_16","alias_value":"MBW3LIJ5GYXQBUZJ","created_at":"2026-07-05T11:28:00Z"},{"alias_kind":"pith_short_8","alias_value":"MBW3LIJ5","created_at":"2026-07-05T11:28:00Z"}],"graph_snapshots":[{"event_id":"sha256:511d75b253339d023f91676b75740363f782801c6fa1272acb390e2c393398b4","target":"graph","created_at":"2026-07-05T11:28:00Z","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/2506.21782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Massively Multi-Task Model-Based Policy Optimization (M3PO), a scalable model-based reinforcement learning (MBRL) framework designed to address sample inefficiency in single-task settings and poor generalization in multi-task domains. Existing model-based approaches like DreamerV3 rely on pixel-level generative models that neglect control-centric representations, while model-free methods such as PPO suffer from high sample complexity and weak exploration. M3PO integrates an implicit world model, trained to predict task outcomes without observation reconstruction, with a hybrid exp","authors_text":"Aditya Narendra, Aleksandr Panov, Dmitry Makarov","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T21:39:01Z","title":"M3PO: Massively Multi-Task Model-Based Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21782","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":"sha256:86cbec932be257af3cbfa39a9ee417b8d43c5afd7202de21b4f0132cff9e2ed5","target":"record","created_at":"2026-07-05T11:28:00Z","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":"8f892230db0242756ddbbc82572ff43b185997ee966e0832aeb213e42dbf64cf","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T21:39:01Z","title_canon_sha256":"18bb3269119cd5dd99c626764b993459cbc4b7bcf564d4f00a96c7c68e254c61"},"schema_version":"1.0","source":{"id":"2506.21782","kind":"arxiv","version":1}},"canonical_sha256":"606db5a13d362f00d32954dd1523e1a946a85e20f47b6bb81fd54c6e0ea768e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"606db5a13d362f00d32954dd1523e1a946a85e20f47b6bb81fd54c6e0ea768e2","first_computed_at":"2026-07-05T11:28:00.975027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:00.975027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bqjdA3/xKSKwklHjf3hGKDysFQQa25zgqqDNPv/i38lW/cZn/6VPJDXY9Mt8wsegTS1Z4u7efH+4+jdqv4W/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:00.975523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86cbec932be257af3cbfa39a9ee417b8d43c5afd7202de21b4f0132cff9e2ed5","sha256:511d75b253339d023f91676b75740363f782801c6fa1272acb390e2c393398b4"],"state_sha256":"ad49932c99c6826ed1d7aefafe2a1550b84e77db1363d4b7e53da4c1af5ff574"}