{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CKDCPHTVOE3O4CTO65TTGPJRFG","short_pith_number":"pith:CKDCPHTV","canonical_record":{"source":{"id":"2405.04342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T14:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"22d4a0d3424f2369b31b75a1a0888154a2a8bfb12792d9575f2aae358202fd8e","abstract_canon_sha256":"3ea2970274549601f3d6df651fe2ff587f14d39acecb2d987a7e6a823fff0d47"},"schema_version":"1.0"},"canonical_sha256":"1286279e757136ee0a6ef767333d3129af6de0a5966a80f71bb77293ff83f1f0","source":{"kind":"arxiv","id":"2405.04342","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04342","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04342v1","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04342","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"CKDCPHTVOE3O","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"CKDCPHTVOE3O4CTO","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"CKDCPHTV","created_at":"2026-07-05T08:16:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CKDCPHTVOE3O4CTO65TTGPJRFG","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T14:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"22d4a0d3424f2369b31b75a1a0888154a2a8bfb12792d9575f2aae358202fd8e","abstract_canon_sha256":"3ea2970274549601f3d6df651fe2ff587f14d39acecb2d987a7e6a823fff0d47"},"schema_version":"1.0"},"canonical_sha256":"1286279e757136ee0a6ef767333d3129af6de0a5966a80f71bb77293ff83f1f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:35.742047Z","signature_b64":"GuXtHDDyDTMQTh5eZ1aGerLmSCqxfgo3nhTCshW3iwoS4OgRxbMkjrMrc89O2fpSoRGJjKeMYxa0nl4KNhstCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1286279e757136ee0a6ef767333d3129af6de0a5966a80f71bb77293ff83f1f0","last_reissued_at":"2026-07-05T08:16:35.741622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:35.741622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04342","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":"2026-07-05T08:16:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ekRAvQ7rDkyLIWCfYwyHe4BahiFZn3JWS+49mi4+gGJQyeN4pT3yBTNkd0+R8Lo/5juhHPX8tw3GT2hxooBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:02:22.801058Z"},"content_sha256":"056356a9cd344ed0ab429156924fedfc76e254863cbc7ebdce2105e4bc9ed9bf","schema_version":"1.0","event_id":"sha256:056356a9cd344ed0ab429156924fedfc76e254863cbc7ebdce2105e4bc9ed9bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CKDCPHTVOE3O4CTO65TTGPJRFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Curse of Diversity in Ensemble-Based Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Evgenii Nikishin, Pierluca D'Oro, Zhixuan Lin","submitted_at":"2024-05-07T14:14:50Z","abstract_excerpt":"We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents -- a well-established exploration strategy -- can significantly impair the performance of the individual ensemble members when compared to standard single-agent training. Through careful analysis, we attribute the degradation in performance to the low proportion of self-generated data in the shared training data for each ensemble member, as well as the inefficiency of the individual ensemble members to learn from such highly off-policy data. We thus name this phenomenon the cur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04342","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.04342/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":"2026-07-05T08:16:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZISHOjQ+TwLKLy7t97ieJ3eYYm9mgvkQ5QszrVyvjLh7E99KDWT6xbIerLs5a6dIhZQNB7SjFjCK/N0+0JfCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:02:22.801446Z"},"content_sha256":"6d6ea70edbaadac461ccd625bca4cce9e09ea24f90b9c40ad5636209b614f2e9","schema_version":"1.0","event_id":"sha256:6d6ea70edbaadac461ccd625bca4cce9e09ea24f90b9c40ad5636209b614f2e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/bundle.json","state_url":"https://pith.science/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/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":"2026-08-06T08:02:22Z","links":{"resolver":"https://pith.science/pith/CKDCPHTVOE3O4CTO65TTGPJRFG","bundle":"https://pith.science/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/bundle.json","state":"https://pith.science/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKDCPHTVOE3O4CTO65TTGPJRFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CKDCPHTVOE3O4CTO65TTGPJRFG","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":"3ea2970274549601f3d6df651fe2ff587f14d39acecb2d987a7e6a823fff0d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T14:14:50Z","title_canon_sha256":"22d4a0d3424f2369b31b75a1a0888154a2a8bfb12792d9575f2aae358202fd8e"},"schema_version":"1.0","source":{"id":"2405.04342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04342","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04342v1","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04342","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"CKDCPHTVOE3O","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"CKDCPHTVOE3O4CTO","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"CKDCPHTV","created_at":"2026-07-05T08:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:6d6ea70edbaadac461ccd625bca4cce9e09ea24f90b9c40ad5636209b614f2e9","target":"graph","created_at":"2026-07-05T08:16:35Z","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/2405.04342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents -- a well-established exploration strategy -- can significantly impair the performance of the individual ensemble members when compared to standard single-agent training. Through careful analysis, we attribute the degradation in performance to the low proportion of self-generated data in the shared training data for each ensemble member, as well as the inefficiency of the individual ensemble members to learn from such highly off-policy data. We thus name this phenomenon the cur","authors_text":"Aaron Courville, Evgenii Nikishin, Pierluca D'Oro, Zhixuan Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T14:14:50Z","title":"The Curse of Diversity in Ensemble-Based Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04342","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":"sha256:056356a9cd344ed0ab429156924fedfc76e254863cbc7ebdce2105e4bc9ed9bf","target":"record","created_at":"2026-07-05T08:16:35Z","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":"3ea2970274549601f3d6df651fe2ff587f14d39acecb2d987a7e6a823fff0d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T14:14:50Z","title_canon_sha256":"22d4a0d3424f2369b31b75a1a0888154a2a8bfb12792d9575f2aae358202fd8e"},"schema_version":"1.0","source":{"id":"2405.04342","kind":"arxiv","version":1}},"canonical_sha256":"1286279e757136ee0a6ef767333d3129af6de0a5966a80f71bb77293ff83f1f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1286279e757136ee0a6ef767333d3129af6de0a5966a80f71bb77293ff83f1f0","first_computed_at":"2026-07-05T08:16:35.741622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:35.741622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GuXtHDDyDTMQTh5eZ1aGerLmSCqxfgo3nhTCshW3iwoS4OgRxbMkjrMrc89O2fpSoRGJjKeMYxa0nl4KNhstCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:35.742047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:056356a9cd344ed0ab429156924fedfc76e254863cbc7ebdce2105e4bc9ed9bf","sha256:6d6ea70edbaadac461ccd625bca4cce9e09ea24f90b9c40ad5636209b614f2e9"],"state_sha256":"e497c93cd386dd5e907e0387026400db3493133db5afb258c6b51a1f0ad8a517"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pxMYUnIpL/UYyMQWRA4J9BGVaooASMIQfu+5WUbdTfmTib8Ourp8glp87vLr0ZFXmHRJuVTCEYmthAyAoDQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:02:22.805788Z","bundle_sha256":"398eec4be3bdf25341b9856f1f553e9188579f301beb69db716b5904cb70a24d"}}