{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:A25TWZQN2JPTGOSCYQIT4ZWJQ6","short_pith_number":"pith:A25TWZQN","canonical_record":{"source":{"id":"2002.00632","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-03T10:09:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"34cef845c8e8cf4ddf7ebf81074110eeb56d5728acf1372cb7b5b8aa09e90593","abstract_canon_sha256":"8fdcd90555bc368e7affa29b48d2b70d4e472cc03dce2a144b63d429597d2a95"},"schema_version":"1.0"},"canonical_sha256":"06bb3b660dd25f333a42c4113e66c987a43572d150b811316ed75f2e22dc4f8d","source":{"kind":"arxiv","id":"2002.00632","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.00632","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2002.00632v3","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.00632","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"A25TWZQN2JPT","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"A25TWZQN2JPTGOSC","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"A25TWZQN","created_at":"2026-07-05T01:41:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:A25TWZQN2JPTGOSCYQIT4ZWJQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2002.00632","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-03T10:09:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"34cef845c8e8cf4ddf7ebf81074110eeb56d5728acf1372cb7b5b8aa09e90593","abstract_canon_sha256":"8fdcd90555bc368e7affa29b48d2b70d4e472cc03dce2a144b63d429597d2a95"},"schema_version":"1.0"},"canonical_sha256":"06bb3b660dd25f333a42c4113e66c987a43572d150b811316ed75f2e22dc4f8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:07.525626Z","signature_b64":"fOUK3LP606qzkrfKpQyPVhWyA5oDQ4H6+MQ0Daoe2oImj2kS25tKCyTASyseJjD49Gvh/WT15iixuErInBAeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bb3b660dd25f333a42c4113e66c987a43572d150b811316ed75f2e22dc4f8d","last_reissued_at":"2026-07-05T01:41:07.525259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:07.525259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.00632","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgkCDw+nskRw2oUL7ZSlOYagN39DH7ppMeVsC2O/VqpAME+2b4s1gdvNA9E7OsR//luFNdbrk8rkUosTQ+7UAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:12:37.368942Z"},"content_sha256":"1de603495ea58c72d2847678087775cfaed291f42f9a4b094c53f2193dd8f7a4","schema_version":"1.0","event_id":"sha256:1de603495ea58c72d2847678087775cfaed291f42f9a4b094c53f2193dd8f7a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:A25TWZQN2JPTGOSCYQIT4ZWJQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Diversity in Population Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts","submitted_at":"2020-02-03T10:09:16Z","abstract_excerpt":"Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected with a diverse set of behaviors. This behavioral diversity is often boosted via multi-objective loss functions. However, those approaches typically leverage mean field updates based on pairwise distances, which makes them susceptible to cycling behaviors and increased redundancy. In addition, explicitly boosting diversity often has a detrimental impact on optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.00632","kind":"arxiv","version":3},"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/2002.00632/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":"2026-07-05T01:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ee18zvEosjdbdCGqLBGxKkfG8ehrC9NOq/cRgxH/iribrjnB+alW6ymvjOk3jIFuLSvp4giX9CARfWRVK+WVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:12:37.370077Z"},"content_sha256":"3327398efaf080ea488306608239dc12daf2129aac11f8ba57807b595773e432","schema_version":"1.0","event_id":"sha256:3327398efaf080ea488306608239dc12daf2129aac11f8ba57807b595773e432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/bundle.json","state_url":"https://pith.science/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/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":"2026-08-17T22:12:37Z","links":{"resolver":"https://pith.science/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6","bundle":"https://pith.science/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/bundle.json","state":"https://pith.science/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A25TWZQN2JPTGOSCYQIT4ZWJQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A25TWZQN2JPTGOSCYQIT4ZWJQ6","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":"8fdcd90555bc368e7affa29b48d2b70d4e472cc03dce2a144b63d429597d2a95","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-03T10:09:16Z","title_canon_sha256":"34cef845c8e8cf4ddf7ebf81074110eeb56d5728acf1372cb7b5b8aa09e90593"},"schema_version":"1.0","source":{"id":"2002.00632","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.00632","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2002.00632v3","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.00632","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"A25TWZQN2JPT","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"A25TWZQN2JPTGOSC","created_at":"2026-07-05T01:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"A25TWZQN","created_at":"2026-07-05T01:41:07Z"}],"graph_snapshots":[{"event_id":"sha256:3327398efaf080ea488306608239dc12daf2129aac11f8ba57807b595773e432","target":"graph","created_at":"2026-07-05T01:41:07Z","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/2002.00632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected with a diverse set of behaviors. This behavioral diversity is often boosted via multi-objective loss functions. However, those approaches typically leverage mean field updates based on pairwise distances, which makes them susceptible to cycling behaviors and increased redundancy. In addition, explicitly boosting diversity often has a detrimental impact on optim","authors_text":"Aldo Pacchiano, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-03T10:09:16Z","title":"Effective Diversity in Population Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.00632","kind":"arxiv","version":3},"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":"sha256:1de603495ea58c72d2847678087775cfaed291f42f9a4b094c53f2193dd8f7a4","target":"record","created_at":"2026-07-05T01:41:07Z","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":"8fdcd90555bc368e7affa29b48d2b70d4e472cc03dce2a144b63d429597d2a95","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-03T10:09:16Z","title_canon_sha256":"34cef845c8e8cf4ddf7ebf81074110eeb56d5728acf1372cb7b5b8aa09e90593"},"schema_version":"1.0","source":{"id":"2002.00632","kind":"arxiv","version":3}},"canonical_sha256":"06bb3b660dd25f333a42c4113e66c987a43572d150b811316ed75f2e22dc4f8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06bb3b660dd25f333a42c4113e66c987a43572d150b811316ed75f2e22dc4f8d","first_computed_at":"2026-07-05T01:41:07.525259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:07.525259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fOUK3LP606qzkrfKpQyPVhWyA5oDQ4H6+MQ0Daoe2oImj2kS25tKCyTASyseJjD49Gvh/WT15iixuErInBAeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:07.525626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.00632","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1de603495ea58c72d2847678087775cfaed291f42f9a4b094c53f2193dd8f7a4","sha256:3327398efaf080ea488306608239dc12daf2129aac11f8ba57807b595773e432"],"state_sha256":"aa60c2b96c2c34992e4fb2aab53fc396d6fb2ec4df9023f670f0291f9b6439b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kOpod1PisTgyCyOIztBdAH6iAR1YYi1m4myGzExdMHIccNd49tik0/zGjBUuD+ELdSsK4chw0vSNLkx5ePvNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:12:37.376200Z","bundle_sha256":"feeb709c1b298c5cae2dc7a8d5b2ec09b6b4447e1a372a08b751fa39d5abc7dc"}}