{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K5MGXJY4A44HQVCGT4NI2A7WLD","short_pith_number":"pith:K5MGXJY4","canonical_record":{"source":{"id":"2403.09859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T20:40:36Z","cross_cats_sorted":[],"title_canon_sha256":"a6980b9fb9cd78eb5789cdf777e8318e4a27a9342ba0dec48069eb7172277b82","abstract_canon_sha256":"4021b3cf7bb55f694a7e9e686f1384e2b58ff864c0e92cef69c6a99829fe4e0d"},"schema_version":"1.0"},"canonical_sha256":"57586ba71c07387854469f1a8d03f658da697cd05b0d6ad910a6263a19a2dd07","source":{"kind":"arxiv","id":"2403.09859","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09859","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09859v1","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09859","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"K5MGXJY4A44H","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"K5MGXJY4A44HQVCG","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"K5MGXJY4","created_at":"2026-07-05T07:56:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K5MGXJY4A44HQVCGT4NI2A7WLD","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T20:40:36Z","cross_cats_sorted":[],"title_canon_sha256":"a6980b9fb9cd78eb5789cdf777e8318e4a27a9342ba0dec48069eb7172277b82","abstract_canon_sha256":"4021b3cf7bb55f694a7e9e686f1384e2b58ff864c0e92cef69c6a99829fe4e0d"},"schema_version":"1.0"},"canonical_sha256":"57586ba71c07387854469f1a8d03f658da697cd05b0d6ad910a6263a19a2dd07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:26.504769Z","signature_b64":"CNAmmfiwHxUf3Xz3WkDtD69JE+znnoOaYwrceSgg5bVj0jLUXys45xTZohkLqkus/GpX8Kw8qDhit8MhQA4pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57586ba71c07387854469f1a8d03f658da697cd05b0d6ad910a6263a19a2dd07","last_reissued_at":"2026-07-05T07:56:26.504275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:26.504275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09859","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":"2026-07-05T07:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfkqFL0gzTqGFdrkoSD9PIcFBjjmrkD7q/VTHBkbLMB4jR2t5WWtx6U12UObvA074g9+3ROzscKXOaoTox5NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:14:01.543726Z"},"content_sha256":"4c72c69662b62aff2769ae8559f0ab6bbdb235be6663a1ce7d5f9d82f50d2c7b","schema_version":"1.0","event_id":"sha256:4c72c69662b62aff2769ae8559f0ab6bbdb235be6663a1ce7d5f9d82f50d2c7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K5MGXJY4A44HQVCGT4NI2A7WLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Gilad Adler, Orr Krupnik, Tom Jurgenson, Zohar Rimon","submitted_at":"2024-03-14T20:40:36Z","abstract_excerpt":"Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional task distributions. In parallel, model-based RL methods have been successful in solving partially observable MDPs, of which meta-RL is a special case. In this work, we leverage this success and propose a new model-based approach to meta-RL, based on elements from existing state-of-the-art model-based and meta-RL methods. We demonstrate the effectiveness of our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09859","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/2403.09859/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":"2026-07-05T07:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWs1Ipaouq5fwGJxzrab/czZ2J+O/cYFLOTs7HcD1BtpBHHZpm41mu1ky2M50mKQZOb0xFR7rqE42hrC+ToUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:14:01.544223Z"},"content_sha256":"9219d59cd47a1d6535dc9ecafefd89abfab061151442c82ab40f9209b45dd93a","schema_version":"1.0","event_id":"sha256:9219d59cd47a1d6535dc9ecafefd89abfab061151442c82ab40f9209b45dd93a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/bundle.json","state_url":"https://pith.science/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/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":"2026-08-21T12:14:01Z","links":{"resolver":"https://pith.science/pith/K5MGXJY4A44HQVCGT4NI2A7WLD","bundle":"https://pith.science/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/bundle.json","state":"https://pith.science/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5MGXJY4A44HQVCGT4NI2A7WLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K5MGXJY4A44HQVCGT4NI2A7WLD","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":"4021b3cf7bb55f694a7e9e686f1384e2b58ff864c0e92cef69c6a99829fe4e0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T20:40:36Z","title_canon_sha256":"a6980b9fb9cd78eb5789cdf777e8318e4a27a9342ba0dec48069eb7172277b82"},"schema_version":"1.0","source":{"id":"2403.09859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09859","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09859v1","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09859","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"K5MGXJY4A44H","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"K5MGXJY4A44HQVCG","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"K5MGXJY4","created_at":"2026-07-05T07:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:9219d59cd47a1d6535dc9ecafefd89abfab061151442c82ab40f9209b45dd93a","target":"graph","created_at":"2026-07-05T07:56:26Z","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/2403.09859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional task distributions. In parallel, model-based RL methods have been successful in solving partially observable MDPs, of which meta-RL is a special case. In this work, we leverage this success and propose a new model-based approach to meta-RL, based on elements from existing state-of-the-art model-based and meta-RL methods. We demonstrate the effectiveness of our ","authors_text":"Aviv Tamar, Gilad Adler, Orr Krupnik, Tom Jurgenson, Zohar Rimon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T20:40:36Z","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09859","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":"sha256:4c72c69662b62aff2769ae8559f0ab6bbdb235be6663a1ce7d5f9d82f50d2c7b","target":"record","created_at":"2026-07-05T07:56:26Z","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":"4021b3cf7bb55f694a7e9e686f1384e2b58ff864c0e92cef69c6a99829fe4e0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T20:40:36Z","title_canon_sha256":"a6980b9fb9cd78eb5789cdf777e8318e4a27a9342ba0dec48069eb7172277b82"},"schema_version":"1.0","source":{"id":"2403.09859","kind":"arxiv","version":1}},"canonical_sha256":"57586ba71c07387854469f1a8d03f658da697cd05b0d6ad910a6263a19a2dd07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57586ba71c07387854469f1a8d03f658da697cd05b0d6ad910a6263a19a2dd07","first_computed_at":"2026-07-05T07:56:26.504275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:26.504275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CNAmmfiwHxUf3Xz3WkDtD69JE+znnoOaYwrceSgg5bVj0jLUXys45xTZohkLqkus/GpX8Kw8qDhit8MhQA4pAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:26.504769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c72c69662b62aff2769ae8559f0ab6bbdb235be6663a1ce7d5f9d82f50d2c7b","sha256:9219d59cd47a1d6535dc9ecafefd89abfab061151442c82ab40f9209b45dd93a"],"state_sha256":"c57c6f1352f879fd411f94ab1a3a2f66c048b70bc0a531c3b53fc3c2515c807c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+ixOk3EBCWH4d0IxyXkek3OeyrbPgjmWscUs4eWJ9FBtuAgSNNiQKelgoIzTtm6330xw+IMtGOaTkuOsuCpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T12:14:01.548448Z","bundle_sha256":"ba5320f3dd89e044dca7a302423fdd5fec9dc80493d891f3a556ed1198633e54"}}