{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4I7VUJEE5QTBFCZHQWCQ2N4YUG","short_pith_number":"pith:4I7VUJEE","canonical_record":{"source":{"id":"2205.15623","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T09:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"40b115f9ba197c24d2b72589827c4a9f4dd92c7583d5c1a456a721c0141ae7c5","abstract_canon_sha256":"cbf5b9b1a07c916508a9d8b90add3bf87d84d840df87b2d1306cf0b2009565ae"},"schema_version":"1.0"},"canonical_sha256":"e23f5a2484ec26128b2785850d3798a1bfa86bdaa02d658d72a5bf489c4f1032","source":{"kind":"arxiv","id":"2205.15623","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15623","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15623v4","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15623","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"4I7VUJEE5QTB","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_16","alias_value":"4I7VUJEE5QTBFCZH","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_8","alias_value":"4I7VUJEE","created_at":"2026-07-05T07:09:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4I7VUJEE5QTBFCZHQWCQ2N4YUG","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15623","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T09:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"40b115f9ba197c24d2b72589827c4a9f4dd92c7583d5c1a456a721c0141ae7c5","abstract_canon_sha256":"cbf5b9b1a07c916508a9d8b90add3bf87d84d840df87b2d1306cf0b2009565ae"},"schema_version":"1.0"},"canonical_sha256":"e23f5a2484ec26128b2785850d3798a1bfa86bdaa02d658d72a5bf489c4f1032","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:42.550996Z","signature_b64":"uaB6L/6TobjyRgF9pjdtjoypb7oJqS/dcXjRgNiEKxvdt+fL0Wt9GbEmkl+BeiL7mtwjnynRmB+ZaQuI1prHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e23f5a2484ec26128b2785850d3798a1bfa86bdaa02d658d72a5bf489c4f1032","last_reissued_at":"2026-07-05T07:09:42.550500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:42.550500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15623","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXg6GhvyCVC3WCPWgY1nC7O9lkoVdVmr1qBzNhStkHoTAPagzlllIXRQiqDmprteKw5/ExE337fg8EKJD0tSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:27:05.668373Z"},"content_sha256":"05c59cd37d26f9135fff8c0951ed68f82823ba369aa124fd751f1234788520fc","schema_version":"1.0","event_id":"sha256:05c59cd37d26f9135fff8c0951ed68f82823ba369aa124fd751f1234788520fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4I7VUJEE5QTBFCZHQWCQ2N4YUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"k-Means Maximum Entropy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Nedergaard, Matthew Cook","submitted_at":"2022-05-31T09:05:58Z","abstract_excerpt":"Exploration in high-dimensional, continuous spaces with sparse rewards is an open problem in reinforcement learning. Artificial curiosity algorithms address this by creating rewards that lead to exploration. Given a reinforcement learning algorithm capable of maximizing rewards, the problem reduces to finding an optimization objective consistent with exploration. Maximum entropy exploration uses the entropy of the state visitation distribution as such an objective. However, efficiently estimating the entropy of the state visitation distribution is challenging in high-dimensional, continuous sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15623","kind":"arxiv","version":4},"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/2205.15623/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":"2026-07-05T07:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewIo+6Ev/4hFq0E/RAdhvsMiVP91YSJuoi3xVbDLgH7LU5cVIthsvARZtNAIn7I9j3axJWF54V+1uLl0HKutDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:27:05.669155Z"},"content_sha256":"28ffbed6867e60a7b6649184ccbb26f202130277245427167e0e34005a2c0a9a","schema_version":"1.0","event_id":"sha256:28ffbed6867e60a7b6649184ccbb26f202130277245427167e0e34005a2c0a9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/bundle.json","state_url":"https://pith.science/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/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":"2026-08-18T20:27:05Z","links":{"resolver":"https://pith.science/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG","bundle":"https://pith.science/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/bundle.json","state":"https://pith.science/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4I7VUJEE5QTBFCZHQWCQ2N4YUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4I7VUJEE5QTBFCZHQWCQ2N4YUG","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":"cbf5b9b1a07c916508a9d8b90add3bf87d84d840df87b2d1306cf0b2009565ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T09:05:58Z","title_canon_sha256":"40b115f9ba197c24d2b72589827c4a9f4dd92c7583d5c1a456a721c0141ae7c5"},"schema_version":"1.0","source":{"id":"2205.15623","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15623","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15623v4","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15623","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"4I7VUJEE5QTB","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_16","alias_value":"4I7VUJEE5QTBFCZH","created_at":"2026-07-05T07:09:42Z"},{"alias_kind":"pith_short_8","alias_value":"4I7VUJEE","created_at":"2026-07-05T07:09:42Z"}],"graph_snapshots":[{"event_id":"sha256:28ffbed6867e60a7b6649184ccbb26f202130277245427167e0e34005a2c0a9a","target":"graph","created_at":"2026-07-05T07:09:42Z","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/2205.15623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration in high-dimensional, continuous spaces with sparse rewards is an open problem in reinforcement learning. Artificial curiosity algorithms address this by creating rewards that lead to exploration. Given a reinforcement learning algorithm capable of maximizing rewards, the problem reduces to finding an optimization objective consistent with exploration. Maximum entropy exploration uses the entropy of the state visitation distribution as such an objective. However, efficiently estimating the entropy of the state visitation distribution is challenging in high-dimensional, continuous sp","authors_text":"Alexander Nedergaard, Matthew Cook","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T09:05:58Z","title":"k-Means Maximum Entropy Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15623","kind":"arxiv","version":4},"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":"sha256:05c59cd37d26f9135fff8c0951ed68f82823ba369aa124fd751f1234788520fc","target":"record","created_at":"2026-07-05T07:09:42Z","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":"cbf5b9b1a07c916508a9d8b90add3bf87d84d840df87b2d1306cf0b2009565ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T09:05:58Z","title_canon_sha256":"40b115f9ba197c24d2b72589827c4a9f4dd92c7583d5c1a456a721c0141ae7c5"},"schema_version":"1.0","source":{"id":"2205.15623","kind":"arxiv","version":4}},"canonical_sha256":"e23f5a2484ec26128b2785850d3798a1bfa86bdaa02d658d72a5bf489c4f1032","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e23f5a2484ec26128b2785850d3798a1bfa86bdaa02d658d72a5bf489c4f1032","first_computed_at":"2026-07-05T07:09:42.550500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:42.550500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uaB6L/6TobjyRgF9pjdtjoypb7oJqS/dcXjRgNiEKxvdt+fL0Wt9GbEmkl+BeiL7mtwjnynRmB+ZaQuI1prHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:42.550996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15623","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05c59cd37d26f9135fff8c0951ed68f82823ba369aa124fd751f1234788520fc","sha256:28ffbed6867e60a7b6649184ccbb26f202130277245427167e0e34005a2c0a9a"],"state_sha256":"f06b295b9834027d29d725186cced2a209c192260ef1d3511c3b226454dd2d9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+JxKkrJO8IWQ3EMOM7uiUtvpPavLuanQnmlVj1Nnm2zMGS28Y6XSwDZbSNCmEKJ3JgON/q5kRXgJUqHgxZTlBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:27:05.674689Z","bundle_sha256":"60b06b3f10508098af5d6ac429d46ad05d6625c5d6b7a6e647f0a6daa163f8e2"}}