{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EJB73BZCGL65XDBC4WP7CKGD7M","short_pith_number":"pith:EJB73BZC","canonical_record":{"source":{"id":"1801.07440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"27896d83833a11ac8cbda5c0a3743da7abbb3a98160948000822f74a851d66d6","abstract_canon_sha256":"2cd63b9a854f69bccd323261327de9fc3746e41d8efe41f02a75506498c2e29c"},"schema_version":"1.0"},"canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","source":{"kind":"arxiv","id":"1801.07440","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07440","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07440v2","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07440","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"EJB73BZCGL65","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EJB73BZCGL65XDBC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EJB73BZC","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EJB73BZCGL65XDBC4WP7CKGD7M","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"27896d83833a11ac8cbda5c0a3743da7abbb3a98160948000822f74a851d66d6","abstract_canon_sha256":"2cd63b9a854f69bccd323261327de9fc3746e41d8efe41f02a75506498c2e29c"},"schema_version":"1.0"},"canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:09.398241Z","signature_b64":"PqMTDq1ajq7watUpwty4W2+a5VotHCJluzT6Qp/7vpfiuYxHiib6gNzffdXPzEOVlqcXLteYkhwKKhlRPCKTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","last_reissued_at":"2026-05-18T00:24:09.397503Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:09.397503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07440","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":"2026-05-18T00:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2yvgcJmnuZGXJL7Q+fqWsCMKIpv+eGwOOjvCqODcyWrsVSv+Fw2bh4iAU2jCiKekOBM/iV7vcMDoFVVDgm/PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:34:43.608958Z"},"content_sha256":"5ef344dfd0ab60b35418d26ee80039943fe474505393123343f60715be5066b2","schema_version":"1.0","event_id":"sha256:5ef344dfd0ab60b35418d26ee80039943fe474505393123343f60715be5066b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EJB73BZCGL65XDBC4WP7CKGD7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curiosity-driven reinforcement learning with homeostatic regulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ildefons Magrans de Abril, Ryota Kanai","submitted_at":"2018-01-23T08:52:22Z","abstract_excerpt":"We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional homeostatic drive to enhance the overall information gain of a reinforcement learning agent interacting with a complex environment using continuous actions. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of information gain and ii) to simplify the computation of the local rewards by avoiding the approximation of comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07440","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":""},"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":"2026-05-18T00:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFbfPcM9B3Kn2DK5GHBdsejAhKe5DXB+dZs9VhSbDMk/K0APoqdxG8Pkx1zO7915FVOvmWFw/UvEL9oABvOvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:34:43.609303Z"},"content_sha256":"6f23445648f52d9507e65a8783aeac30d822d52116c3aac4a4d1fc73c3f51191","schema_version":"1.0","event_id":"sha256:6f23445648f52d9507e65a8783aeac30d822d52116c3aac4a4d1fc73c3f51191"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/bundle.json","state_url":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJB73BZCGL65XDBC4WP7CKGD7M/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":"2026-06-03T05:34:43Z","links":{"resolver":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M","bundle":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/bundle.json","state":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJB73BZCGL65XDBC4WP7CKGD7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EJB73BZCGL65XDBC4WP7CKGD7M","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":"2cd63b9a854f69bccd323261327de9fc3746e41d8efe41f02a75506498c2e29c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","title_canon_sha256":"27896d83833a11ac8cbda5c0a3743da7abbb3a98160948000822f74a851d66d6"},"schema_version":"1.0","source":{"id":"1801.07440","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07440","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07440v2","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07440","created_at":"2026-05-18T00:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"EJB73BZCGL65","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EJB73BZCGL65XDBC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EJB73BZC","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:6f23445648f52d9507e65a8783aeac30d822d52116c3aac4a4d1fc73c3f51191","target":"graph","created_at":"2026-05-18T00:24:09Z","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"},"paper":{"abstract_excerpt":"We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional homeostatic drive to enhance the overall information gain of a reinforcement learning agent interacting with a complex environment using continuous actions. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of information gain and ii) to simplify the computation of the local rewards by avoiding the approximation of comple","authors_text":"Ildefons Magrans de Abril, Ryota Kanai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","title":"Curiosity-driven reinforcement learning with homeostatic regulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07440","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":"sha256:5ef344dfd0ab60b35418d26ee80039943fe474505393123343f60715be5066b2","target":"record","created_at":"2026-05-18T00:24:09Z","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":"2cd63b9a854f69bccd323261327de9fc3746e41d8efe41f02a75506498c2e29c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","title_canon_sha256":"27896d83833a11ac8cbda5c0a3743da7abbb3a98160948000822f74a851d66d6"},"schema_version":"1.0","source":{"id":"1801.07440","kind":"arxiv","version":2}},"canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","first_computed_at":"2026-05-18T00:24:09.397503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:09.397503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PqMTDq1ajq7watUpwty4W2+a5VotHCJluzT6Qp/7vpfiuYxHiib6gNzffdXPzEOVlqcXLteYkhwKKhlRPCKTDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:09.398241Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07440","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ef344dfd0ab60b35418d26ee80039943fe474505393123343f60715be5066b2","sha256:6f23445648f52d9507e65a8783aeac30d822d52116c3aac4a4d1fc73c3f51191"],"state_sha256":"68214ad8b026aa348fd47b59c2a26c90ec63296af3f2091c13686a5913e75a53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRru0cWXYsOEScire0zT69MvBj5YBIELm8eFfQ8XTV1nF60pALxB4T/opRUnG3SA3esTr6Axju9YS3Kcvlq4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T05:34:43.611407Z","bundle_sha256":"b3394dfa14f365d3f6c670bb421f159365cc1230062c2125fcb3d88d49bc64f0"}}