{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VRHV5YRFQNA5WTHHI2GXKZZCMK","short_pith_number":"pith:VRHV5YRF","canonical_record":{"source":{"id":"2206.03192","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T11:27:40Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a4a57a67b249b39701fc75245f40934c50fd2f09bffc0e98045d4928224abba7","abstract_canon_sha256":"08b8bd3c72ac52ed6d516519a81de5d20600643955929178ebb865c1573f9bea"},"schema_version":"1.0"},"canonical_sha256":"ac4f5ee2258341db4ce7468d75672262b8fef44ebba7a2a4808a40834f0329e7","source":{"kind":"arxiv","id":"2206.03192","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03192","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03192v4","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03192","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"VRHV5YRFQNA5","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"VRHV5YRFQNA5WTHH","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"VRHV5YRF","created_at":"2026-07-05T04:33:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VRHV5YRFQNA5WTHHI2GXKZZCMK","target":"record","payload":{"canonical_record":{"source":{"id":"2206.03192","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T11:27:40Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a4a57a67b249b39701fc75245f40934c50fd2f09bffc0e98045d4928224abba7","abstract_canon_sha256":"08b8bd3c72ac52ed6d516519a81de5d20600643955929178ebb865c1573f9bea"},"schema_version":"1.0"},"canonical_sha256":"ac4f5ee2258341db4ce7468d75672262b8fef44ebba7a2a4808a40834f0329e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:00.557919Z","signature_b64":"AkWL/81zp66RTgAhldXEpz72VqJcH5276B/1oCJLw5u5zkwOq0A6FV6Qr+zQLl24xUuQXsW+Wv08Oxb+VxXlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4f5ee2258341db4ce7468d75672262b8fef44ebba7a2a4808a40834f0329e7","last_reissued_at":"2026-07-05T04:33:00.557495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:00.557495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.03192","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":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SMoHxT5NRknGThbQD9LZiVJcRsIo7utpSvYHD+4vrhsmbk1FAhtrUYaz04IwAH/i8fChLoYC55LHYDuo09+lDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:50:30.814285Z"},"content_sha256":"08851a9b34197c15da6e0defae37096b44b86fbf3670f059761c08ede7822af8","schema_version":"1.0","event_id":"sha256:08851a9b34197c15da6e0defae37096b44b86fbf3670f059761c08ede7822af8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VRHV5YRFQNA5WTHHI2GXKZZCMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Data Distribution Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Changnan Xiao, Jiajun Fan","submitted_at":"2022-06-07T11:27:40Z","abstract_excerpt":"To obtain higher sample efficiency and superior final performance simultaneously has been one of the major challenges for deep reinforcement learning (DRL). Previous work could handle one of these challenges but typically failed to address them concurrently. In this paper, we try to tackle these two challenges simultaneously. To achieve this, we firstly decouple these challenges into two classic RL problems: data richness and exploration-exploitation trade-off. Then, we cast these two problems into the training data distribution optimization problem, namely to obtain desired training data with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03192","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/2206.03192/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":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G/cH97i3/4oEL9hsQIABcwyDYbTNVHSeonYR3oOsrhi7CtuHmpL5Zu+zm1dJAJRusm2tY6x85Qhao23dVdIOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:50:30.814739Z"},"content_sha256":"1a22065c534af4ffcdc07dbb562b2f1727d551917350fb3fedbfbb111e07ca72","schema_version":"1.0","event_id":"sha256:1a22065c534af4ffcdc07dbb562b2f1727d551917350fb3fedbfbb111e07ca72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/bundle.json","state_url":"https://pith.science/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/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":"2026-07-31T17:50:30Z","links":{"resolver":"https://pith.science/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK","bundle":"https://pith.science/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/bundle.json","state":"https://pith.science/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VRHV5YRFQNA5WTHHI2GXKZZCMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VRHV5YRFQNA5WTHHI2GXKZZCMK","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":"08b8bd3c72ac52ed6d516519a81de5d20600643955929178ebb865c1573f9bea","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T11:27:40Z","title_canon_sha256":"a4a57a67b249b39701fc75245f40934c50fd2f09bffc0e98045d4928224abba7"},"schema_version":"1.0","source":{"id":"2206.03192","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03192","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03192v4","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03192","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"VRHV5YRFQNA5","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"VRHV5YRFQNA5WTHH","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"VRHV5YRF","created_at":"2026-07-05T04:33:00Z"}],"graph_snapshots":[{"event_id":"sha256:1a22065c534af4ffcdc07dbb562b2f1727d551917350fb3fedbfbb111e07ca72","target":"graph","created_at":"2026-07-05T04:33:00Z","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/2206.03192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To obtain higher sample efficiency and superior final performance simultaneously has been one of the major challenges for deep reinforcement learning (DRL). Previous work could handle one of these challenges but typically failed to address them concurrently. In this paper, we try to tackle these two challenges simultaneously. To achieve this, we firstly decouple these challenges into two classic RL problems: data richness and exploration-exploitation trade-off. Then, we cast these two problems into the training data distribution optimization problem, namely to obtain desired training data with","authors_text":"Changnan Xiao, Jiajun Fan","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T11:27:40Z","title":"Generalized Data Distribution Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03192","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":"sha256:08851a9b34197c15da6e0defae37096b44b86fbf3670f059761c08ede7822af8","target":"record","created_at":"2026-07-05T04:33:00Z","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":"08b8bd3c72ac52ed6d516519a81de5d20600643955929178ebb865c1573f9bea","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T11:27:40Z","title_canon_sha256":"a4a57a67b249b39701fc75245f40934c50fd2f09bffc0e98045d4928224abba7"},"schema_version":"1.0","source":{"id":"2206.03192","kind":"arxiv","version":4}},"canonical_sha256":"ac4f5ee2258341db4ce7468d75672262b8fef44ebba7a2a4808a40834f0329e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac4f5ee2258341db4ce7468d75672262b8fef44ebba7a2a4808a40834f0329e7","first_computed_at":"2026-07-05T04:33:00.557495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:00.557495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AkWL/81zp66RTgAhldXEpz72VqJcH5276B/1oCJLw5u5zkwOq0A6FV6Qr+zQLl24xUuQXsW+Wv08Oxb+VxXlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:00.557919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03192","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08851a9b34197c15da6e0defae37096b44b86fbf3670f059761c08ede7822af8","sha256:1a22065c534af4ffcdc07dbb562b2f1727d551917350fb3fedbfbb111e07ca72"],"state_sha256":"3a29ff59fe546109b6805a89e3b54f7d1ea8897e067965f2298d52a1114244d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uQ/90Es9EJhozFUsEjMlywVRGezFdh/ahLwOqOpCm+FK6rSTgYDdD2du5rUOYDHmBvdTzIS+r3e+GcCGWiUGBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:50:30.819030Z","bundle_sha256":"4fff5d400247feda14504c19b2bee114d143fc584998ab1505df47cfc2e99cf5"}}