{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EW5U7FAXVA4HRZAVYU44XVUKIT","short_pith_number":"pith:EW5U7FAX","canonical_record":{"source":{"id":"2003.05325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:25:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aea2c609240a7e52634046fea7fe4e7908b8ec06821419a632bdb59291b15d87","abstract_canon_sha256":"502a97135fd7255ea9f0980733af8b850f0753bb1f33acf2134892e7983c561e"},"schema_version":"1.0"},"canonical_sha256":"25bb4f9417a83878e415c539cbd68a44c84c8b7dbac64e3102ef1ebd089a4313","source":{"kind":"arxiv","id":"2003.05325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05325","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05325v1","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05325","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"EW5U7FAXVA4H","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_16","alias_value":"EW5U7FAXVA4HRZAV","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_8","alias_value":"EW5U7FAX","created_at":"2026-07-05T00:47:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EW5U7FAXVA4HRZAVYU44XVUKIT","target":"record","payload":{"canonical_record":{"source":{"id":"2003.05325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:25:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aea2c609240a7e52634046fea7fe4e7908b8ec06821419a632bdb59291b15d87","abstract_canon_sha256":"502a97135fd7255ea9f0980733af8b850f0753bb1f33acf2134892e7983c561e"},"schema_version":"1.0"},"canonical_sha256":"25bb4f9417a83878e415c539cbd68a44c84c8b7dbac64e3102ef1ebd089a4313","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:23.295041Z","signature_b64":"V+Hjazx7iZ9ovTFjJIx76Ax8OgZb+rjC7xDYHfaS+ZvzPtMtOghFTw3eGrjOIGMoiJTiOX6G5DbGtZmBQLi0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25bb4f9417a83878e415c539cbd68a44c84c8b7dbac64e3102ef1ebd089a4313","last_reissued_at":"2026-07-05T00:47:23.294610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:23.294610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.05325","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":"2026-07-05T00:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/VU070/5EIaYJPip81W980bmggdIhIY7md73W/FjYgYpqwQBxyEGf6c5HA0kOtA/YrzOLs1Chaz6Yl3zzjNrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:10:55.623612Z"},"content_sha256":"2c913c05e8ecae3bcbf5e7b2ca9dda27c521cfbab5e2b7eb72e0cf34a1098cc3","schema_version":"1.0","event_id":"sha256:2c913c05e8ecae3bcbf5e7b2ca9dda27c521cfbab5e2b7eb72e0cf34a1098cc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EW5U7FAXVA4HRZAVYU44XVUKIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-learning curiosity algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ferran Alet, Leslie Pack Kaelbling, Martin F. Schneider, Tomas Lozano-Perez","submitted_at":"2020-03-11T14:25:43Z","abstract_excerpt":"We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We formulate the problem of generating curious behavior as one of meta-learning: an outer loop will search over a space of curiosity mechanisms that dynamically adapt the agent's reward signal, and an inner loop will perform standard reinforcement learning using the adapted reward signal. However, current meta-RL methods based on transferring neural network weig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05325","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/2003.05325/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":"2026-07-05T00:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x7dkA+fdZCibIGZ1AWUK/hCd9prhnGB4XKMyh/eSfamjjfZrRDvQUXiFU5/CYmVM8NeCJ6OF32hHPpk3gVfjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:10:55.624109Z"},"content_sha256":"18c3101984cbdb277efdc73ad0f8ba0478ee5f143a413b69c3d32e23b180c02b","schema_version":"1.0","event_id":"sha256:18c3101984cbdb277efdc73ad0f8ba0478ee5f143a413b69c3d32e23b180c02b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/bundle.json","state_url":"https://pith.science/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/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":"2026-08-09T20:10:55Z","links":{"resolver":"https://pith.science/pith/EW5U7FAXVA4HRZAVYU44XVUKIT","bundle":"https://pith.science/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/bundle.json","state":"https://pith.science/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EW5U7FAXVA4HRZAVYU44XVUKIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EW5U7FAXVA4HRZAVYU44XVUKIT","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":"502a97135fd7255ea9f0980733af8b850f0753bb1f33acf2134892e7983c561e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:25:43Z","title_canon_sha256":"aea2c609240a7e52634046fea7fe4e7908b8ec06821419a632bdb59291b15d87"},"schema_version":"1.0","source":{"id":"2003.05325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05325","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05325v1","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05325","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"EW5U7FAXVA4H","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_16","alias_value":"EW5U7FAXVA4HRZAV","created_at":"2026-07-05T00:47:23Z"},{"alias_kind":"pith_short_8","alias_value":"EW5U7FAX","created_at":"2026-07-05T00:47:23Z"}],"graph_snapshots":[{"event_id":"sha256:18c3101984cbdb277efdc73ad0f8ba0478ee5f143a413b69c3d32e23b180c02b","target":"graph","created_at":"2026-07-05T00:47:23Z","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/2003.05325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We formulate the problem of generating curious behavior as one of meta-learning: an outer loop will search over a space of curiosity mechanisms that dynamically adapt the agent's reward signal, and an inner loop will perform standard reinforcement learning using the adapted reward signal. However, current meta-RL methods based on transferring neural network weig","authors_text":"Ferran Alet, Leslie Pack Kaelbling, Martin F. Schneider, Tomas Lozano-Perez","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:25:43Z","title":"Meta-learning curiosity algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05325","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":"sha256:2c913c05e8ecae3bcbf5e7b2ca9dda27c521cfbab5e2b7eb72e0cf34a1098cc3","target":"record","created_at":"2026-07-05T00:47:23Z","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":"502a97135fd7255ea9f0980733af8b850f0753bb1f33acf2134892e7983c561e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:25:43Z","title_canon_sha256":"aea2c609240a7e52634046fea7fe4e7908b8ec06821419a632bdb59291b15d87"},"schema_version":"1.0","source":{"id":"2003.05325","kind":"arxiv","version":1}},"canonical_sha256":"25bb4f9417a83878e415c539cbd68a44c84c8b7dbac64e3102ef1ebd089a4313","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25bb4f9417a83878e415c539cbd68a44c84c8b7dbac64e3102ef1ebd089a4313","first_computed_at":"2026-07-05T00:47:23.294610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:23.294610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V+Hjazx7iZ9ovTFjJIx76Ax8OgZb+rjC7xDYHfaS+ZvzPtMtOghFTw3eGrjOIGMoiJTiOX6G5DbGtZmBQLi0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:23.295041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.05325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c913c05e8ecae3bcbf5e7b2ca9dda27c521cfbab5e2b7eb72e0cf34a1098cc3","sha256:18c3101984cbdb277efdc73ad0f8ba0478ee5f143a413b69c3d32e23b180c02b"],"state_sha256":"8ccaee97314779aba35d794281eee3dcfbe599ec135f89518334a5678cff2102"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Giq6ZshhPdglJg9eDo++UX+4ziavp6mO/5e7NObMJzj6DE97ovFxn1pBHJQr4UQAURlCCZxKLjVaxI3XkPGMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:10:55.627745Z","bundle_sha256":"8574232db9f05d0fdd30548b08da1e50f7daf6db4d6d05be1244897d42e8afc4"}}