{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2QMYX45VRW4D65CZBCNY4MGTVB","short_pith_number":"pith:2QMYX45V","canonical_record":{"source":{"id":"2506.05716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:36:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d83a3f21b116ce0728a918ab082a9257ec79c94676da0ca88de0c34326bde0d","abstract_canon_sha256":"6b85f4fbd6280db4949ad75323a57c10c52aecdf4e346ee4a33d1d323f37d818"},"schema_version":"1.0"},"canonical_sha256":"d4198bf3b58db83f7459089b8e30d3a8632ad9b85c31ef8dcc5ccb22fdb9050e","source":{"kind":"arxiv","id":"2506.05716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05716","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05716v1","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05716","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"2QMYX45VRW4D","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"2QMYX45VRW4D65CZ","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"2QMYX45V","created_at":"2026-07-05T11:17:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2QMYX45VRW4D65CZBCNY4MGTVB","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:36:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d83a3f21b116ce0728a918ab082a9257ec79c94676da0ca88de0c34326bde0d","abstract_canon_sha256":"6b85f4fbd6280db4949ad75323a57c10c52aecdf4e346ee4a33d1d323f37d818"},"schema_version":"1.0"},"canonical_sha256":"d4198bf3b58db83f7459089b8e30d3a8632ad9b85c31ef8dcc5ccb22fdb9050e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:08.575929Z","signature_b64":"MTvNQmpeiTegUUNB/knPNPHN2N+bOVXaJpsfnXGE9tn07r6o4zSbk+9MsNFDF8Db/1LPa2tIKff6Ehwk0GhxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4198bf3b58db83f7459089b8e30d3a8632ad9b85c31ef8dcc5ccb22fdb9050e","last_reissued_at":"2026-07-05T11:17:08.575470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:08.575470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05716","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":"2026-07-05T11:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rdg6RxJigIIsNJFWncV+Sg5sSDsppcy3oz8Y4wxEIgUZaRffsqOst87CQJzLJjx6lwgq+SPdySKfNy3IFexdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:08:44.511111Z"},"content_sha256":"995a4b5c65d647555eb0af652a86eea03e848a5dba5f76199250c0847a28d6cc","schema_version":"1.0","event_id":"sha256:995a4b5c65d647555eb0af652a86eea03e848a5dba5f76199250c0847a28d6cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2QMYX45VRW4D65CZBCNY4MGTVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Elastic DQN: A novel multi-step ensemble approach to address overestimation in deep value-based reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrian Ly, Francisco Cruz, Peter Vamplew, Richard Dazeley, Sunil Aryal","submitted_at":"2025-06-06T03:36:19Z","abstract_excerpt":"While many algorithmic extensions to Deep Q-Networks (DQN) have been proposed, there remains limited understanding of how different improvements interact. In particular, multi-step and ensemble style extensions have shown promise in reducing overestimation bias, thereby improving sample efficiency and algorithmic stability. In this paper, we introduce a novel algorithm called Ensemble Elastic Step DQN (EEDQN), which unifies ensembles with elastic step updates to stabilise algorithmic performance. EEDQN is designed to address two major challenges in deep reinforcement learning: overestimation b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05716","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/2506.05716/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":"2026-07-05T11:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6P3cF5+S2Q3JOl/FncB7fG4UuzekLx0fENDjZPEsWMf6E/j3Mnl6cxM31+1cZpnosjBXEj/S61PGEgD228YBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:08:44.511608Z"},"content_sha256":"4837aa9e700d63d6c80ee4da5d8aac3bdea02c7899f06cd28d0aed87d24e6633","schema_version":"1.0","event_id":"sha256:4837aa9e700d63d6c80ee4da5d8aac3bdea02c7899f06cd28d0aed87d24e6633"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QMYX45VRW4D65CZBCNY4MGTVB/bundle.json","state_url":"https://pith.science/pith/2QMYX45VRW4D65CZBCNY4MGTVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QMYX45VRW4D65CZBCNY4MGTVB/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":"2026-08-08T22:08:44Z","links":{"resolver":"https://pith.science/pith/2QMYX45VRW4D65CZBCNY4MGTVB","bundle":"https://pith.science/pith/2QMYX45VRW4D65CZBCNY4MGTVB/bundle.json","state":"https://pith.science/pith/2QMYX45VRW4D65CZBCNY4MGTVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QMYX45VRW4D65CZBCNY4MGTVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2QMYX45VRW4D65CZBCNY4MGTVB","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":"6b85f4fbd6280db4949ad75323a57c10c52aecdf4e346ee4a33d1d323f37d818","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:36:19Z","title_canon_sha256":"2d83a3f21b116ce0728a918ab082a9257ec79c94676da0ca88de0c34326bde0d"},"schema_version":"1.0","source":{"id":"2506.05716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05716","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05716v1","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05716","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"2QMYX45VRW4D","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"2QMYX45VRW4D65CZ","created_at":"2026-07-05T11:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"2QMYX45V","created_at":"2026-07-05T11:17:08Z"}],"graph_snapshots":[{"event_id":"sha256:4837aa9e700d63d6c80ee4da5d8aac3bdea02c7899f06cd28d0aed87d24e6633","target":"graph","created_at":"2026-07-05T11:17:08Z","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/2506.05716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While many algorithmic extensions to Deep Q-Networks (DQN) have been proposed, there remains limited understanding of how different improvements interact. In particular, multi-step and ensemble style extensions have shown promise in reducing overestimation bias, thereby improving sample efficiency and algorithmic stability. In this paper, we introduce a novel algorithm called Ensemble Elastic Step DQN (EEDQN), which unifies ensembles with elastic step updates to stabilise algorithmic performance. EEDQN is designed to address two major challenges in deep reinforcement learning: overestimation b","authors_text":"Adrian Ly, Francisco Cruz, Peter Vamplew, Richard Dazeley, Sunil Aryal","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:36:19Z","title":"Ensemble Elastic DQN: A novel multi-step ensemble approach to address overestimation in deep value-based reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05716","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":"sha256:995a4b5c65d647555eb0af652a86eea03e848a5dba5f76199250c0847a28d6cc","target":"record","created_at":"2026-07-05T11:17:08Z","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":"6b85f4fbd6280db4949ad75323a57c10c52aecdf4e346ee4a33d1d323f37d818","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:36:19Z","title_canon_sha256":"2d83a3f21b116ce0728a918ab082a9257ec79c94676da0ca88de0c34326bde0d"},"schema_version":"1.0","source":{"id":"2506.05716","kind":"arxiv","version":1}},"canonical_sha256":"d4198bf3b58db83f7459089b8e30d3a8632ad9b85c31ef8dcc5ccb22fdb9050e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4198bf3b58db83f7459089b8e30d3a8632ad9b85c31ef8dcc5ccb22fdb9050e","first_computed_at":"2026-07-05T11:17:08.575470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:08.575470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MTvNQmpeiTegUUNB/knPNPHN2N+bOVXaJpsfnXGE9tn07r6o4zSbk+9MsNFDF8Db/1LPa2tIKff6Ehwk0GhxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:08.575929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:995a4b5c65d647555eb0af652a86eea03e848a5dba5f76199250c0847a28d6cc","sha256:4837aa9e700d63d6c80ee4da5d8aac3bdea02c7899f06cd28d0aed87d24e6633"],"state_sha256":"28ced9ccc551d758e6caef305bcd27b6d9e5efab27e6e15320675e411ec5dd83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agswPCr2K+JJyiHzZI8vCYc15n/VpFNfQ+fZ4omLGnpY49q1LqTz4yKy/WpwWNExj+LeblIIw1YwzdCYlt5oDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:08:44.515299Z","bundle_sha256":"c69d300be3ba36e037b4bcf2bde2cc5038b0658daf8043289e82cbe4ddc36a50"}}