{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EL453F25VA3LGDTK2KH2LNJVIF","short_pith_number":"pith:EL453F25","canonical_record":{"source":{"id":"2209.00532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T15:27:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57957d0810bf84c9e64ca3447b332e81ac2cf57855767114d0527e332b89caa8","abstract_canon_sha256":"29420c197ff86d96b3a8f023a7188d81b5752d87414774dfced363eae30bf8b4"},"schema_version":"1.0"},"canonical_sha256":"22f9dd975da836b30e6ad28fa5b53541670308f072756ffe76fd42e190fbb76f","source":{"kind":"arxiv","id":"2209.00532","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00532","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00532v1","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00532","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_12","alias_value":"EL453F25VA3L","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_16","alias_value":"EL453F25VA3LGDTK","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_8","alias_value":"EL453F25","created_at":"2026-07-05T04:53:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EL453F25VA3LGDTK2KH2LNJVIF","target":"record","payload":{"canonical_record":{"source":{"id":"2209.00532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T15:27:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57957d0810bf84c9e64ca3447b332e81ac2cf57855767114d0527e332b89caa8","abstract_canon_sha256":"29420c197ff86d96b3a8f023a7188d81b5752d87414774dfced363eae30bf8b4"},"schema_version":"1.0"},"canonical_sha256":"22f9dd975da836b30e6ad28fa5b53541670308f072756ffe76fd42e190fbb76f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:51.094362Z","signature_b64":"1/cI849XmLKyahKnEu8pbBOmvyUWWXSrjtN948SPz8VTMMtVeBpNQStUZKa+j8GW7YnDXB4s85vLOc3SfpyYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22f9dd975da836b30e6ad28fa5b53541670308f072756ffe76fd42e190fbb76f","last_reissued_at":"2026-07-05T04:53:51.093964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:51.093964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.00532","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":"2026-07-05T04:53:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsGRo+xe5OPc0GWXg16Ry6LA8LCbRIi3qKa7KtH4W4n7FEqhCnDsIXIbSrEeu60FDNCI/mgvtj47S54CQGvsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:24:43.065391Z"},"content_sha256":"c9eb1c057a4e93edab5984cb18ed05505ebba19d568f3c75eb9e2ca18a70be39","schema_version":"1.0","event_id":"sha256:c9eb1c057a4e93edab5984cb18ed05505ebba19d568f3c75eb9e2ca18a70be39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EL453F25VA3LGDTK2KH2LNJVIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actor Prioritized Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat","submitted_at":"2022-09-01T15:27:46Z","abstract_excerpt":"A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. Although it has been shown that PER is one of the most crucial components for the overall performance of deep RL methods in discrete action domains, many empirical studies indicate that it considerably underperforms actor-critic algorithms in continuous control. We theoretically show that actor networks cannot be effectively trained with transitions that have la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00532","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/2209.00532/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":"2026-07-05T04:53:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkvVAg1GdKsWm9gmjF3N6ZarmbUKzIPt8zAIbdlyLEnwI12xM18lJI90TDwEbNibmPtHJqKOSsqaS5vkEYD/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:24:43.065789Z"},"content_sha256":"a4040b8017330ba76daf28cdae27b04ccd54a1fc7af3aa44db7fd8361cd7b570","schema_version":"1.0","event_id":"sha256:a4040b8017330ba76daf28cdae27b04ccd54a1fc7af3aa44db7fd8361cd7b570"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EL453F25VA3LGDTK2KH2LNJVIF/bundle.json","state_url":"https://pith.science/pith/EL453F25VA3LGDTK2KH2LNJVIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EL453F25VA3LGDTK2KH2LNJVIF/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":"2026-08-23T02:24:43Z","links":{"resolver":"https://pith.science/pith/EL453F25VA3LGDTK2KH2LNJVIF","bundle":"https://pith.science/pith/EL453F25VA3LGDTK2KH2LNJVIF/bundle.json","state":"https://pith.science/pith/EL453F25VA3LGDTK2KH2LNJVIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EL453F25VA3LGDTK2KH2LNJVIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EL453F25VA3LGDTK2KH2LNJVIF","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":"29420c197ff86d96b3a8f023a7188d81b5752d87414774dfced363eae30bf8b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T15:27:46Z","title_canon_sha256":"57957d0810bf84c9e64ca3447b332e81ac2cf57855767114d0527e332b89caa8"},"schema_version":"1.0","source":{"id":"2209.00532","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00532","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00532v1","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00532","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_12","alias_value":"EL453F25VA3L","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_16","alias_value":"EL453F25VA3LGDTK","created_at":"2026-07-05T04:53:51Z"},{"alias_kind":"pith_short_8","alias_value":"EL453F25","created_at":"2026-07-05T04:53:51Z"}],"graph_snapshots":[{"event_id":"sha256:a4040b8017330ba76daf28cdae27b04ccd54a1fc7af3aa44db7fd8361cd7b570","target":"graph","created_at":"2026-07-05T04:53:51Z","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/2209.00532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. Although it has been shown that PER is one of the most crucial components for the overall performance of deep RL methods in discrete action domains, many empirical studies indicate that it considerably underperforms actor-critic algorithms in continuous control. We theoretically show that actor networks cannot be effectively trained with transitions that have la","authors_text":"Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T15:27:46Z","title":"Actor Prioritized Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00532","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:c9eb1c057a4e93edab5984cb18ed05505ebba19d568f3c75eb9e2ca18a70be39","target":"record","created_at":"2026-07-05T04:53:51Z","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":"29420c197ff86d96b3a8f023a7188d81b5752d87414774dfced363eae30bf8b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T15:27:46Z","title_canon_sha256":"57957d0810bf84c9e64ca3447b332e81ac2cf57855767114d0527e332b89caa8"},"schema_version":"1.0","source":{"id":"2209.00532","kind":"arxiv","version":1}},"canonical_sha256":"22f9dd975da836b30e6ad28fa5b53541670308f072756ffe76fd42e190fbb76f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22f9dd975da836b30e6ad28fa5b53541670308f072756ffe76fd42e190fbb76f","first_computed_at":"2026-07-05T04:53:51.093964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:51.093964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/cI849XmLKyahKnEu8pbBOmvyUWWXSrjtN948SPz8VTMMtVeBpNQStUZKa+j8GW7YnDXB4s85vLOc3SfpyYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:51.094362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.00532","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9eb1c057a4e93edab5984cb18ed05505ebba19d568f3c75eb9e2ca18a70be39","sha256:a4040b8017330ba76daf28cdae27b04ccd54a1fc7af3aa44db7fd8361cd7b570"],"state_sha256":"4a435cd837ee2315abcb7db45dc032becc2728c4212ccb3f075a8f7b4b61bad0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOUaUNZKMdzvBdn5sesuUZKEoOM1HyYz5pn3mAoFqiWMKgMlTXyeivLHZ+mAHRVXZ4h2Kna8bn2PYSivSSN/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:24:43.068882Z","bundle_sha256":"ed1ca8b4ecfe25ca5ad203cf80367af341adc4ff3d5301e95e2b6fbf5e37fe6b"}}