{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7MIGKFK2X522WQ6UOLSH6RVQUL","short_pith_number":"pith:7MIGKFK2","canonical_record":{"source":{"id":"2008.02598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0","abstract_canon_sha256":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74"},"schema_version":"1.0"},"canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","source":{"kind":"arxiv","id":"2008.02598","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02598v3","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"7MIGKFK2X522","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"7MIGKFK2X522WQ6U","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"7MIGKFK2","created_at":"2026-07-05T02:14:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7MIGKFK2X522WQ6UOLSH6RVQUL","target":"record","payload":{"canonical_record":{"source":{"id":"2008.02598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0","abstract_canon_sha256":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74"},"schema_version":"1.0"},"canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:42.810133Z","signature_b64":"twg6ulUW/f/BbxDh0OrBgH25L4HaIBN0b/tfI5P2RpTHnWdbrqzlBKmBdkOQKLr1t5ud+Qwrfnfjc+ZcbZahBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","last_reissued_at":"2026-07-05T02:14:42.809681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:42.809681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.02598","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FOOVuqb3NuqzYFA9gJq1+O5ITQfLuUuXSKAZ0v5ik7ONKlc0TwFmOzMXeXFltwBley6/X1gNyLN75kXUcKnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:21:59.004054Z"},"content_sha256":"933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a","schema_version":"1.0","event_id":"sha256:933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7MIGKFK2X522WQ6UOLSH6RVQUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Meta Learning of Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Idan Shenfeld, Ron Dorfman","submitted_at":"2020-08-06T12:09:18Z","abstract_excerpt":"Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward in a new, unseen task from the same task distribution. In particular, while each conventional RL agent explored and exploited its own different task, the meta-agent must identify regularities in the data that lead to effective exploration/exploitation in the unseen task. Here, we take a Bayesian RL (BRL) view, and seek to learn a Bayes-optimal policy from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02598","kind":"arxiv","version":3},"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/2008.02598/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":"2026-07-05T02:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lioY36kb962AYx8tJ8iU/a2u/b1P5NIfDDUOjaqqRkuXnh/gF0rkjd/UueTnNjvyiGAA0AVafD19etfmq2Y0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:21:59.005045Z"},"content_sha256":"f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8","schema_version":"1.0","event_id":"sha256:f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/bundle.json","state_url":"https://pith.science/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/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":"2026-08-09T11:21:59Z","links":{"resolver":"https://pith.science/pith/7MIGKFK2X522WQ6UOLSH6RVQUL","bundle":"https://pith.science/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/bundle.json","state":"https://pith.science/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MIGKFK2X522WQ6UOLSH6RVQUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7MIGKFK2X522WQ6UOLSH6RVQUL","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":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0"},"schema_version":"1.0","source":{"id":"2008.02598","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02598v3","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"7MIGKFK2X522","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"7MIGKFK2X522WQ6U","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"7MIGKFK2","created_at":"2026-07-05T02:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8","target":"graph","created_at":"2026-07-05T02:14:42Z","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/2008.02598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward in a new, unseen task from the same task distribution. In particular, while each conventional RL agent explored and exploited its own different task, the meta-agent must identify regularities in the data that lead to effective exploration/exploitation in the unseen task. Here, we take a Bayesian RL (BRL) view, and seek to learn a Bayes-optimal policy from th","authors_text":"Aviv Tamar, Idan Shenfeld, Ron Dorfman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title":"Offline Meta Learning of Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02598","kind":"arxiv","version":3},"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":"sha256:933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a","target":"record","created_at":"2026-07-05T02:14:42Z","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":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0"},"schema_version":"1.0","source":{"id":"2008.02598","kind":"arxiv","version":3}},"canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","first_computed_at":"2026-07-05T02:14:42.809681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:42.809681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twg6ulUW/f/BbxDh0OrBgH25L4HaIBN0b/tfI5P2RpTHnWdbrqzlBKmBdkOQKLr1t5ud+Qwrfnfjc+ZcbZahBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:42.810133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02598","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a","sha256:f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8"],"state_sha256":"74c166416c87c7f8866d3d61bc5790fe09c645cd5f14c3d15291bab93c473aaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2C3mWSYooSOHFesH3U8dHCc1A8XlSAiDu73uI2wVryZYi3V/uzrX+1MVhK5IY7X6r4PacOqkMagb9aZR6e0QDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:21:59.013886Z","bundle_sha256":"226f271283c9c3c24669fc61e55ddae1d55ab8e5fd8834015c5415100b136dbf"}}