{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PGT3UGKO7HZTRBRN5CY5FNPRAU","short_pith_number":"pith:PGT3UGKO","canonical_record":{"source":{"id":"1810.12162","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T14:43:48Z","cross_cats_sorted":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"title_canon_sha256":"f4f0f9ff043f014c0be946312280cdf8b71e068a7ad1870b3419e94aad3f3168","abstract_canon_sha256":"d871ac2e6651d1b783389645a3c86792389594e86508f6148334ee369d10820a"},"schema_version":"1.0"},"canonical_sha256":"79a7ba194ef9f338862de8b1d2b5f1050b00aff672a0664c99f3e24c94d4642e","source":{"kind":"arxiv","id":"1810.12162","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12162","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12162v5","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12162","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"PGT3UGKO7HZT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PGT3UGKO7HZTRBRN","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PGT3UGKO","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PGT3UGKO7HZTRBRN5CY5FNPRAU","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12162","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T14:43:48Z","cross_cats_sorted":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"title_canon_sha256":"f4f0f9ff043f014c0be946312280cdf8b71e068a7ad1870b3419e94aad3f3168","abstract_canon_sha256":"d871ac2e6651d1b783389645a3c86792389594e86508f6148334ee369d10820a"},"schema_version":"1.0"},"canonical_sha256":"79a7ba194ef9f338862de8b1d2b5f1050b00aff672a0664c99f3e24c94d4642e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.525739Z","signature_b64":"rbYojp6UovsATeK7v+fyq4yX52jW1gDWOb7UDMJmXEJslqMsUU6zVof4osaxKP6j09uE2NgZKQELAsupcWE7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a7ba194ef9f338862de8b1d2b5f1050b00aff672a0664c99f3e24c94d4642e","last_reissued_at":"2026-05-17T23:43:23.525096Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.525096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12162","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+j6xbMgStQ3U2XxQrXIMTUvNEkH/LdWeNQ+AlFCfrsyBxw36Z1ECgJhIA4T7VZADglvwn/KcGznsq94wyPm8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:03:19.779489Z"},"content_sha256":"e4defe26712e52599905409a6fbb5163e3621331e6a14fb7d638e857668d8f33","schema_version":"1.0","event_id":"sha256:e4defe26712e52599905409a6fbb5163e3621331e6a14fb7d638e857668d8f33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PGT3UGKO7HZTRBRN5CY5FNPRAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Active Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faustino Gomez, Pranav Shyam, Wojciech Ja\\'skowski","submitted_at":"2018-10-29T14:43:48Z","abstract_excerpt":"Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward models to plan to observe novel events. This is carried out by optimizing agent behaviour with respect to a measure of novelty derived from the Bayesian perspective of exploration, which is estimated using the disagreement between the futures predicted by the ensemble members. We sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12162","kind":"arxiv","version":5},"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":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qzIj0Cm/mK1TpP+L4WkG3pAxYT8Qjm3pJO27s4F0Uy1hvxfwu3H66+X/Lj6HD2vqfoSstAs1TFVLLj4AiqJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:03:19.779857Z"},"content_sha256":"01a4ab403ac23f060034328163bfffedd47efeb7dd041b905529d644ac658db3","schema_version":"1.0","event_id":"sha256:01a4ab403ac23f060034328163bfffedd47efeb7dd041b905529d644ac658db3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/bundle.json","state_url":"https://pith.science/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/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":"2026-06-12T09:03:19Z","links":{"resolver":"https://pith.science/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU","bundle":"https://pith.science/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/bundle.json","state":"https://pith.science/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGT3UGKO7HZTRBRN5CY5FNPRAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PGT3UGKO7HZTRBRN5CY5FNPRAU","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":"d871ac2e6651d1b783389645a3c86792389594e86508f6148334ee369d10820a","cross_cats_sorted":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T14:43:48Z","title_canon_sha256":"f4f0f9ff043f014c0be946312280cdf8b71e068a7ad1870b3419e94aad3f3168"},"schema_version":"1.0","source":{"id":"1810.12162","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12162","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12162v5","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12162","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"PGT3UGKO7HZT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PGT3UGKO7HZTRBRN","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PGT3UGKO","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:01a4ab403ac23f060034328163bfffedd47efeb7dd041b905529d644ac658db3","target":"graph","created_at":"2026-05-17T23:43:23Z","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"},"paper":{"abstract_excerpt":"Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward models to plan to observe novel events. This is carried out by optimizing agent behaviour with respect to a measure of novelty derived from the Bayesian perspective of exploration, which is estimated using the disagreement between the futures predicted by the ensemble members. We sh","authors_text":"Faustino Gomez, Pranav Shyam, Wojciech Ja\\'skowski","cross_cats":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T14:43:48Z","title":"Model-Based Active Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12162","kind":"arxiv","version":5},"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:e4defe26712e52599905409a6fbb5163e3621331e6a14fb7d638e857668d8f33","target":"record","created_at":"2026-05-17T23:43:23Z","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":"d871ac2e6651d1b783389645a3c86792389594e86508f6148334ee369d10820a","cross_cats_sorted":["cs.AI","cs.IT","cs.NE","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T14:43:48Z","title_canon_sha256":"f4f0f9ff043f014c0be946312280cdf8b71e068a7ad1870b3419e94aad3f3168"},"schema_version":"1.0","source":{"id":"1810.12162","kind":"arxiv","version":5}},"canonical_sha256":"79a7ba194ef9f338862de8b1d2b5f1050b00aff672a0664c99f3e24c94d4642e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79a7ba194ef9f338862de8b1d2b5f1050b00aff672a0664c99f3e24c94d4642e","first_computed_at":"2026-05-17T23:43:23.525096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:23.525096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rbYojp6UovsATeK7v+fyq4yX52jW1gDWOb7UDMJmXEJslqMsUU6zVof4osaxKP6j09uE2NgZKQELAsupcWE7DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:23.525739Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12162","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4defe26712e52599905409a6fbb5163e3621331e6a14fb7d638e857668d8f33","sha256:01a4ab403ac23f060034328163bfffedd47efeb7dd041b905529d644ac658db3"],"state_sha256":"488dba8982e73b859833f0bfe8dbebd03b52d96ba02786246ef65c5ec1cd960b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rObZ387SlTxZmS2rfLXKUBIc0XcHhIlGLdIzl/LsUl+vJGF4NemIO9gO1oFr0GZX2Pn45P9ysd4NSFFaqOA+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T09:03:19.782080Z","bundle_sha256":"d697230bfbd1a8823934dc20a392d519932c18340470e02c31b295356d0b050c"}}