{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CZ6K2D3HQSMMKK6VR6BQSMRSIR","short_pith_number":"pith:CZ6K2D3H","canonical_record":{"source":{"id":"2011.01054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T15:37:37Z","cross_cats_sorted":[],"title_canon_sha256":"061307a17e3e9664ee3aa422b820f12c0b5faca3e1677602d9686edd097a8fcf","abstract_canon_sha256":"c9bc7aafec95a17e6250a0883da6e565babf7b971dd425167e3f9b7001b76b6f"},"schema_version":"1.0"},"canonical_sha256":"167cad0f678498c52bd58f8309323244762e00474968737b4b3ac49d635f39ae","source":{"kind":"arxiv","id":"2011.01054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01054","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01054v2","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01054","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"CZ6K2D3HQSMM","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_16","alias_value":"CZ6K2D3HQSMMKK6V","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_8","alias_value":"CZ6K2D3H","created_at":"2026-07-05T02:54:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CZ6K2D3HQSMMKK6VR6BQSMRSIR","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T15:37:37Z","cross_cats_sorted":[],"title_canon_sha256":"061307a17e3e9664ee3aa422b820f12c0b5faca3e1677602d9686edd097a8fcf","abstract_canon_sha256":"c9bc7aafec95a17e6250a0883da6e565babf7b971dd425167e3f9b7001b76b6f"},"schema_version":"1.0"},"canonical_sha256":"167cad0f678498c52bd58f8309323244762e00474968737b4b3ac49d635f39ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:15.113331Z","signature_b64":"UtXGvIopmKc6GiQ8hKZS+DDP0MueBjCgEkD0wDQ+Qr5vDW0sPAJt5SwZ5sSeY4zneEZQbq9T5pjN75r3lkQwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167cad0f678498c52bd58f8309323244762e00474968737b4b3ac49d635f39ae","last_reissued_at":"2026-07-05T02:54:15.112866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:15.112866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01054","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:54:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zwj5qQ8uT+k/y1NH9X7fa/37bcWutafG3fmGrtnHitfX5MpgaPXXGmohCXagX+WgPTMM+WMDbXQaWWMM0g4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:53:41.590101Z"},"content_sha256":"d2a612c561eb0c79eadc4890ac7884f63bebd7624b3b997d1d8c498f4aebc417","schema_version":"1.0","event_id":"sha256:d2a612c561eb0c79eadc4890ac7884f63bebd7624b3b997d1d8c498f4aebc417"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CZ6K2D3HQSMMKK6VR6BQSMRSIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information-theoretic Task Selection for Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matteo Leonetti, Ricardo Luna Gutierrez","submitted_at":"2020-11-02T15:37:37Z","abstract_excerpt":"In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution of test tasks and hence all used in training. We show that given a set of training tasks, learning can be both faster and more effective (leading to better performance in the test tasks), if the training tasks are appropriately selected. We propose a task selection algorithm, Information-Theoretic Task Selection (ITTS), based on information theory, which opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01054","kind":"arxiv","version":2},"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/2011.01054/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":"2026-07-05T02:54:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4xEcXxrnDMTaaJiFzNoGhNxq65NoITZVF7025oXVjs+ct3GO6195W6uS3cpCb+yzPejVydjJ1wx8su1+f7LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:53:41.590590Z"},"content_sha256":"74eff055c5edcdb12c03a7aaae355b5414e4be48c8fdea569fa0eaebc64e7e62","schema_version":"1.0","event_id":"sha256:74eff055c5edcdb12c03a7aaae355b5414e4be48c8fdea569fa0eaebc64e7e62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/bundle.json","state_url":"https://pith.science/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/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":"2026-08-05T09:53:41Z","links":{"resolver":"https://pith.science/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR","bundle":"https://pith.science/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/bundle.json","state":"https://pith.science/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ6K2D3HQSMMKK6VR6BQSMRSIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CZ6K2D3HQSMMKK6VR6BQSMRSIR","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":"c9bc7aafec95a17e6250a0883da6e565babf7b971dd425167e3f9b7001b76b6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T15:37:37Z","title_canon_sha256":"061307a17e3e9664ee3aa422b820f12c0b5faca3e1677602d9686edd097a8fcf"},"schema_version":"1.0","source":{"id":"2011.01054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01054","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01054v2","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01054","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"CZ6K2D3HQSMM","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_16","alias_value":"CZ6K2D3HQSMMKK6V","created_at":"2026-07-05T02:54:15Z"},{"alias_kind":"pith_short_8","alias_value":"CZ6K2D3H","created_at":"2026-07-05T02:54:15Z"}],"graph_snapshots":[{"event_id":"sha256:74eff055c5edcdb12c03a7aaae355b5414e4be48c8fdea569fa0eaebc64e7e62","target":"graph","created_at":"2026-07-05T02:54:15Z","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/2011.01054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution of test tasks and hence all used in training. We show that given a set of training tasks, learning can be both faster and more effective (leading to better performance in the test tasks), if the training tasks are appropriately selected. We propose a task selection algorithm, Information-Theoretic Task Selection (ITTS), based on information theory, which opt","authors_text":"Matteo Leonetti, Ricardo Luna Gutierrez","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T15:37:37Z","title":"Information-theoretic Task Selection for Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01054","kind":"arxiv","version":2},"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:d2a612c561eb0c79eadc4890ac7884f63bebd7624b3b997d1d8c498f4aebc417","target":"record","created_at":"2026-07-05T02:54:15Z","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":"c9bc7aafec95a17e6250a0883da6e565babf7b971dd425167e3f9b7001b76b6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T15:37:37Z","title_canon_sha256":"061307a17e3e9664ee3aa422b820f12c0b5faca3e1677602d9686edd097a8fcf"},"schema_version":"1.0","source":{"id":"2011.01054","kind":"arxiv","version":2}},"canonical_sha256":"167cad0f678498c52bd58f8309323244762e00474968737b4b3ac49d635f39ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167cad0f678498c52bd58f8309323244762e00474968737b4b3ac49d635f39ae","first_computed_at":"2026-07-05T02:54:15.112866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:15.112866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UtXGvIopmKc6GiQ8hKZS+DDP0MueBjCgEkD0wDQ+Qr5vDW0sPAJt5SwZ5sSeY4zneEZQbq9T5pjN75r3lkQwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:15.113331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2a612c561eb0c79eadc4890ac7884f63bebd7624b3b997d1d8c498f4aebc417","sha256:74eff055c5edcdb12c03a7aaae355b5414e4be48c8fdea569fa0eaebc64e7e62"],"state_sha256":"d04c5f97a3dcddca27e342b2befe1e563419fd8dfa3aeb1f32e924f4dc689268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9sMQwZuJTY36KRrqQFxrFg0z+OlEJ6GtAABDMXrQJ041aTLwT1n5bkORLEfjQiAbceMhbJJg8/WsBmk6Jk1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:53:41.594235Z","bundle_sha256":"ec63b66abb13bbc782312c0506bae8727d254f6b169f5761de19f57364224ba4"}}