{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FQRFVVENTHTTN2KV75SXZHAFXT","short_pith_number":"pith:FQRFVVEN","canonical_record":{"source":{"id":"2106.02613","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T17:21:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2cf7c247c77ed7a74417de6a37814d150458ef2dbd7dcb44e5cc7959c92dacd","abstract_canon_sha256":"90ba40f5de75743e30b636270ab131f2808bda235b3f6c9b9fb66d0ed20cf917"},"schema_version":"1.0"},"canonical_sha256":"2c225ad48d99e736e955ff657c9c05bccbae5b5a945d52c024897ac4c780060b","source":{"kind":"arxiv","id":"2106.02613","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02613","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02613v4","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02613","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_12","alias_value":"FQRFVVENTHTT","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_16","alias_value":"FQRFVVENTHTTN2KV","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_8","alias_value":"FQRFVVEN","created_at":"2026-07-05T06:48:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FQRFVVENTHTTN2KV75SXZHAFXT","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02613","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T17:21:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2cf7c247c77ed7a74417de6a37814d150458ef2dbd7dcb44e5cc7959c92dacd","abstract_canon_sha256":"90ba40f5de75743e30b636270ab131f2808bda235b3f6c9b9fb66d0ed20cf917"},"schema_version":"1.0"},"canonical_sha256":"2c225ad48d99e736e955ff657c9c05bccbae5b5a945d52c024897ac4c780060b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:29.593535Z","signature_b64":"pKWnC6mrVuwvGQRHVdbPanIKEgWmOBk6Q3dSU93G/6NjXMnXntI3zQ1KYYwdjxDd41gcpqZF7MGqn2/e519MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c225ad48d99e736e955ff657c9c05bccbae5b5a945d52c024897ac4c780060b","last_reissued_at":"2026-07-05T06:48:29.593020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:29.593020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02613","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4m/puYQNIuMzhE9mVNbl67E7A2exFRJgtlJ96wKQKJeadaugbVHhHWI7Oo3Ns3NyQ47hWtlE1hT9yj7U3FYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:40:36.557510Z"},"content_sha256":"078b5c6d6f30a7ae3544901af01a76797dbf5c57fa91f1e4382cf8bc5c658081","schema_version":"1.0","event_id":"sha256:078b5c6d6f30a7ae3544901af01a76797dbf5c57fa91f1e4382cf8bc5c658081"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FQRFVVENTHTTN2KV75SXZHAFXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Target Networks and Functional Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Pich\\'e, Christopher Pal, Gian Maria Marconi, Joseph Marino, Mohammad Emtiyaz Khan, Rafael Pardinas, Valentin Thomas","submitted_at":"2021-06-04T17:21:07Z","abstract_excerpt":"Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer which can be beneficial in some cases, but also have disadvantages such as being inflexible and can resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02613","kind":"arxiv","version":4},"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/2106.02613/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":"2026-07-05T06:48:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oF2df22U93J/6sWhdNXeN97hdAxkXKr2d6hpPjMKdb3wCDgOmRcaXGqhTOQc+OGMWAH8WETBtEJwJaG+wryyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:40:36.558418Z"},"content_sha256":"b65c7c92e815b6cd62297dfb6f303b6b385af9d3f27164fe1b424292667f374a","schema_version":"1.0","event_id":"sha256:b65c7c92e815b6cd62297dfb6f303b6b385af9d3f27164fe1b424292667f374a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQRFVVENTHTTN2KV75SXZHAFXT/bundle.json","state_url":"https://pith.science/pith/FQRFVVENTHTTN2KV75SXZHAFXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQRFVVENTHTTN2KV75SXZHAFXT/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":"2026-08-05T04:40:36Z","links":{"resolver":"https://pith.science/pith/FQRFVVENTHTTN2KV75SXZHAFXT","bundle":"https://pith.science/pith/FQRFVVENTHTTN2KV75SXZHAFXT/bundle.json","state":"https://pith.science/pith/FQRFVVENTHTTN2KV75SXZHAFXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQRFVVENTHTTN2KV75SXZHAFXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FQRFVVENTHTTN2KV75SXZHAFXT","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":"90ba40f5de75743e30b636270ab131f2808bda235b3f6c9b9fb66d0ed20cf917","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T17:21:07Z","title_canon_sha256":"a2cf7c247c77ed7a74417de6a37814d150458ef2dbd7dcb44e5cc7959c92dacd"},"schema_version":"1.0","source":{"id":"2106.02613","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02613","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02613v4","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02613","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_12","alias_value":"FQRFVVENTHTT","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_16","alias_value":"FQRFVVENTHTTN2KV","created_at":"2026-07-05T06:48:29Z"},{"alias_kind":"pith_short_8","alias_value":"FQRFVVEN","created_at":"2026-07-05T06:48:29Z"}],"graph_snapshots":[{"event_id":"sha256:b65c7c92e815b6cd62297dfb6f303b6b385af9d3f27164fe1b424292667f374a","target":"graph","created_at":"2026-07-05T06:48:29Z","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/2106.02613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer which can be beneficial in some cases, but also have disadvantages such as being inflexible and can resu","authors_text":"Alexandre Pich\\'e, Christopher Pal, Gian Maria Marconi, Joseph Marino, Mohammad Emtiyaz Khan, Rafael Pardinas, Valentin Thomas","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T17:21:07Z","title":"Bridging the Gap Between Target Networks and Functional Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02613","kind":"arxiv","version":4},"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":"sha256:078b5c6d6f30a7ae3544901af01a76797dbf5c57fa91f1e4382cf8bc5c658081","target":"record","created_at":"2026-07-05T06:48:29Z","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":"90ba40f5de75743e30b636270ab131f2808bda235b3f6c9b9fb66d0ed20cf917","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T17:21:07Z","title_canon_sha256":"a2cf7c247c77ed7a74417de6a37814d150458ef2dbd7dcb44e5cc7959c92dacd"},"schema_version":"1.0","source":{"id":"2106.02613","kind":"arxiv","version":4}},"canonical_sha256":"2c225ad48d99e736e955ff657c9c05bccbae5b5a945d52c024897ac4c780060b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c225ad48d99e736e955ff657c9c05bccbae5b5a945d52c024897ac4c780060b","first_computed_at":"2026-07-05T06:48:29.593020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:29.593020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKWnC6mrVuwvGQRHVdbPanIKEgWmOBk6Q3dSU93G/6NjXMnXntI3zQ1KYYwdjxDd41gcpqZF7MGqn2/e519MBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:29.593535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02613","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:078b5c6d6f30a7ae3544901af01a76797dbf5c57fa91f1e4382cf8bc5c658081","sha256:b65c7c92e815b6cd62297dfb6f303b6b385af9d3f27164fe1b424292667f374a"],"state_sha256":"bd80f225c7adaf5547dbeaea66b71219d961cebd74b481c6990016c5bad9d4a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sNNCpcNAkj//u9dULMdT58k1i3FdX1GmJzOkWia3L8L8TabmE0ieA1T7SWZYnIsDPc5ZUiBWFwVBDOJSQoY4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:40:36.564326Z","bundle_sha256":"79966c758ae1482d475be6477f0a9454dd897b21829c0b74114c8e34ea3eefd9"}}