{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ACCLNSPGAKAQZAHF5XAFIJQVIS","short_pith_number":"pith:ACCLNSPG","canonical_record":{"source":{"id":"1808.07739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T13:24:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"21dac6c3c585665b1bcd5f3ab9a6b8edf512e67f5dc1514d9870a59865b2a33c","abstract_canon_sha256":"fc5bfae8f91c88ff39e7f814676b9e441ed8b3cde7b0e9f9a8040daea4197256"},"schema_version":"1.0"},"canonical_sha256":"0084b6c9e602810c80e5edc0542615449b4282b3342f2a8fd61647d13e01da84","source":{"kind":"arxiv","id":"1808.07739","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07739","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07739v1","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07739","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"ACCLNSPGAKAQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ACCLNSPGAKAQZAHF","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ACCLNSPG","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ACCLNSPGAKAQZAHF5XAFIJQVIS","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T13:24:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"21dac6c3c585665b1bcd5f3ab9a6b8edf512e67f5dc1514d9870a59865b2a33c","abstract_canon_sha256":"fc5bfae8f91c88ff39e7f814676b9e441ed8b3cde7b0e9f9a8040daea4197256"},"schema_version":"1.0"},"canonical_sha256":"0084b6c9e602810c80e5edc0542615449b4282b3342f2a8fd61647d13e01da84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:24.397549Z","signature_b64":"hlxEh2UBnxiZBvs6r31l9JlkhKkgvOzWGD0BUoCTOSNescZxlUMzgFZhT49C14JdHwhgoQTsV7wagtNOt6raAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0084b6c9e602810c80e5edc0542615449b4282b3342f2a8fd61647d13e01da84","last_reissued_at":"2026-05-18T00:07:24.397069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:24.397069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07739","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":"2026-05-18T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mADyJlfSKGH4N5KiznUMsLgYrST+CS1fG0G6fsWWHLmogsu3+IHITFZMcKgtPYMPIorwwX15bgL9p1BwfBjgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:51:35.243668Z"},"content_sha256":"d69c984bf6e272c631d4e9f03095e8b983d68c955a7a862aaf37187816a53e42","schema_version":"1.0","event_id":"sha256:d69c984bf6e272c631d4e9f03095e8b983d68c955a7a862aaf37187816a53e42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ACCLNSPGAKAQZAHF5XAFIJQVIS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabien C. Y. Benureau, Pierre-Yves Oudeyer","submitted_at":"2018-08-23T13:24:17Z","abstract_excerpt":"We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the reward signal is the diversity of effects that each strategy produces. We test the method empirically on a simulated planar robotic arm, and establish that the method is both able discriminate between strategies of dissimilar quality, even when the differences are tenuous, and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07739","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":""},"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":"2026-05-18T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCKaIj9eBZGBINGrRJ2EJvYuZWaMWiTX8vqY4+ppijCZTZ+Pfvm+y2UtepLqNqyr7ELtoNt8Jqt4DmYUDi4qCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:51:35.244098Z"},"content_sha256":"d902b43a6716bc27db7b94e8711a03e90873ebd0dd5268169f81f012be6ef610","schema_version":"1.0","event_id":"sha256:d902b43a6716bc27db7b94e8711a03e90873ebd0dd5268169f81f012be6ef610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/bundle.json","state_url":"https://pith.science/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/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":"2026-06-11T12:51:35Z","links":{"resolver":"https://pith.science/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS","bundle":"https://pith.science/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/bundle.json","state":"https://pith.science/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACCLNSPGAKAQZAHF5XAFIJQVIS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ACCLNSPGAKAQZAHF5XAFIJQVIS","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":"fc5bfae8f91c88ff39e7f814676b9e441ed8b3cde7b0e9f9a8040daea4197256","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T13:24:17Z","title_canon_sha256":"21dac6c3c585665b1bcd5f3ab9a6b8edf512e67f5dc1514d9870a59865b2a33c"},"schema_version":"1.0","source":{"id":"1808.07739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07739","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07739v1","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07739","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"ACCLNSPGAKAQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ACCLNSPGAKAQZAHF","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ACCLNSPG","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:d902b43a6716bc27db7b94e8711a03e90873ebd0dd5268169f81f012be6ef610","target":"graph","created_at":"2026-05-18T00:07:24Z","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 consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the reward signal is the diversity of effects that each strategy produces. We test the method empirically on a simulated planar robotic arm, and establish that the method is both able discriminate between strategies of dissimilar quality, even when the differences are tenuous, and t","authors_text":"Fabien C. Y. Benureau, Pierre-Yves Oudeyer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T13:24:17Z","title":"Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07739","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:d69c984bf6e272c631d4e9f03095e8b983d68c955a7a862aaf37187816a53e42","target":"record","created_at":"2026-05-18T00:07:24Z","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":"fc5bfae8f91c88ff39e7f814676b9e441ed8b3cde7b0e9f9a8040daea4197256","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T13:24:17Z","title_canon_sha256":"21dac6c3c585665b1bcd5f3ab9a6b8edf512e67f5dc1514d9870a59865b2a33c"},"schema_version":"1.0","source":{"id":"1808.07739","kind":"arxiv","version":1}},"canonical_sha256":"0084b6c9e602810c80e5edc0542615449b4282b3342f2a8fd61647d13e01da84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0084b6c9e602810c80e5edc0542615449b4282b3342f2a8fd61647d13e01da84","first_computed_at":"2026-05-18T00:07:24.397069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:24.397069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hlxEh2UBnxiZBvs6r31l9JlkhKkgvOzWGD0BUoCTOSNescZxlUMzgFZhT49C14JdHwhgoQTsV7wagtNOt6raAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:24.397549Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d69c984bf6e272c631d4e9f03095e8b983d68c955a7a862aaf37187816a53e42","sha256:d902b43a6716bc27db7b94e8711a03e90873ebd0dd5268169f81f012be6ef610"],"state_sha256":"251c0c5316f81e3fdc65b8c26e03ec746fc56157adc24f52ffdfb469cbca9472"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIM/M2j+z5ANDLfT8JMty9lv2oxq/FFr+Crbh1BTuqYpDytOuUFSAeB/XF+fRiikbarxEyeAoOpYmr3Pn9WjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:51:35.246294Z","bundle_sha256":"6fb99b1bf1ecdd48649b77b76ab1e160225c5dddbabf0757e71322f8519ae561"}}