{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:THD2AV7E5YLUZKMHCOUMRA2ZEX","short_pith_number":"pith:THD2AV7E","canonical_record":{"source":{"id":"2106.06232","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T08:31:12Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"030c8be1382c1a6da4fa97008c08eb47efbf69ad0ccf4f08d7db4efb6c912270","abstract_canon_sha256":"dab149480ab2ed1e94cba465a64fd16913c389414c2cb3144c5b0d2b1cf4f863"},"schema_version":"1.0"},"canonical_sha256":"99c7a057e4ee174ca98713a8c8835925eb42e384aef578d232844c1125edef4f","source":{"kind":"arxiv","id":"2106.06232","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06232","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06232v6","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06232","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"THD2AV7E5YLU","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"THD2AV7E5YLUZKMH","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"THD2AV7E","created_at":"2026-07-05T03:46:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:THD2AV7E5YLUZKMHCOUMRA2ZEX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06232","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T08:31:12Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"030c8be1382c1a6da4fa97008c08eb47efbf69ad0ccf4f08d7db4efb6c912270","abstract_canon_sha256":"dab149480ab2ed1e94cba465a64fd16913c389414c2cb3144c5b0d2b1cf4f863"},"schema_version":"1.0"},"canonical_sha256":"99c7a057e4ee174ca98713a8c8835925eb42e384aef578d232844c1125edef4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:58.870644Z","signature_b64":"YLEQ7gaeuqBfYwIdVk7WznccUUxgppVFVYShlQwENax2bxlwjWuid4A/jjcD+Yh9d+xye2YOfOqEvhA2A64YAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c7a057e4ee174ca98713a8c8835925eb42e384aef578d232844c1125edef4f","last_reissued_at":"2026-07-05T03:46:58.870154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:58.870154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06232","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wyZztVCgkAeec4h+AjMGKWvEr3IkcHEsqA58ZFn7Svoe+9H/8mC+RjTGWv70JDR0I1q/q81No+dnJSrjlGT/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:43:18.128034Z"},"content_sha256":"73b2b754bfa4bbf96568be3dbafbe9509302f82488170e03036caf228c40f805","schema_version":"1.0","event_id":"sha256:73b2b754bfa4bbf96568be3dbafbe9509302f82488170e03036caf228c40f805"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:THD2AV7E5YLUZKMHCOUMRA2ZEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","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, Yue Huang","submitted_at":"2021-06-11T08:31:12Z","abstract_excerpt":"Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process. DQN found this property might cause instability for training, so it proposed effective methods to handle the downside of the property. Instead of focusing on the unfavourable aspects, we find it critical for RL to ease the gap between the estimated data distribution and the ground truth data distribution while supervised learning (SL) fails to do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06232","kind":"arxiv","version":6},"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/2106.06232/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":"2026-07-05T03:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJA+WMUVP4+o5abiUL+qqrnHTJkwGwetifI0yNm/vume51BMzYIoq+qcU/OVGf6AtbJTu7vCch6KVboYXcwhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:43:18.128431Z"},"content_sha256":"7d0ed8d350b288acc12a20b483c6acba42c954d4efd31dc8740bd5058b7b6665","schema_version":"1.0","event_id":"sha256:7d0ed8d350b288acc12a20b483c6acba42c954d4efd31dc8740bd5058b7b6665"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/bundle.json","state_url":"https://pith.science/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/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":"2026-07-09T01:43:18Z","links":{"resolver":"https://pith.science/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX","bundle":"https://pith.science/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/bundle.json","state":"https://pith.science/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THD2AV7E5YLUZKMHCOUMRA2ZEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:THD2AV7E5YLUZKMHCOUMRA2ZEX","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":"dab149480ab2ed1e94cba465a64fd16913c389414c2cb3144c5b0d2b1cf4f863","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T08:31:12Z","title_canon_sha256":"030c8be1382c1a6da4fa97008c08eb47efbf69ad0ccf4f08d7db4efb6c912270"},"schema_version":"1.0","source":{"id":"2106.06232","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06232","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06232v6","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06232","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"THD2AV7E5YLU","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"THD2AV7E5YLUZKMH","created_at":"2026-07-05T03:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"THD2AV7E","created_at":"2026-07-05T03:46:58Z"}],"graph_snapshots":[{"event_id":"sha256:7d0ed8d350b288acc12a20b483c6acba42c954d4efd31dc8740bd5058b7b6665","target":"graph","created_at":"2026-07-05T03:46:58Z","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/2106.06232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process. DQN found this property might cause instability for training, so it proposed effective methods to handle the downside of the property. Instead of focusing on the unfavourable aspects, we find it critical for RL to ease the gap between the estimated data distribution and the ground truth data distribution while supervised learning (SL) fails to do","authors_text":"Changnan Xiao, Jiajun Fan, Yue Huang","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T08:31:12Z","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06232","kind":"arxiv","version":6},"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":"sha256:73b2b754bfa4bbf96568be3dbafbe9509302f82488170e03036caf228c40f805","target":"record","created_at":"2026-07-05T03:46:58Z","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":"dab149480ab2ed1e94cba465a64fd16913c389414c2cb3144c5b0d2b1cf4f863","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T08:31:12Z","title_canon_sha256":"030c8be1382c1a6da4fa97008c08eb47efbf69ad0ccf4f08d7db4efb6c912270"},"schema_version":"1.0","source":{"id":"2106.06232","kind":"arxiv","version":6}},"canonical_sha256":"99c7a057e4ee174ca98713a8c8835925eb42e384aef578d232844c1125edef4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99c7a057e4ee174ca98713a8c8835925eb42e384aef578d232844c1125edef4f","first_computed_at":"2026-07-05T03:46:58.870154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:58.870154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YLEQ7gaeuqBfYwIdVk7WznccUUxgppVFVYShlQwENax2bxlwjWuid4A/jjcD+Yh9d+xye2YOfOqEvhA2A64YAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:58.870644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06232","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73b2b754bfa4bbf96568be3dbafbe9509302f82488170e03036caf228c40f805","sha256:7d0ed8d350b288acc12a20b483c6acba42c954d4efd31dc8740bd5058b7b6665"],"state_sha256":"9a1e7533252a64155e9eca2ee4076c4a7368f4602af67122531b438827164f07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nCZyihwOXQd93PprQFFwHv9nx7h7zC6AU0u70X6qxOZnEd0M0eZlY2ZYJQPRy6UNW8aAFNvzQfFH0Ff8GuWADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:43:18.130509Z","bundle_sha256":"ca1e8c82c95342a9fecca8e5988714dc2949d7080f96125e21e9c9372d1e99f1"}}