{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4EZT76WGKDKFREI4TMKJMVVRDF","short_pith_number":"pith:4EZT76WG","canonical_record":{"source":{"id":"2309.04707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-09T07:19:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25bfd5d0a3e6f7e9d055af383282adabaf0fd864297581d72a50cc9331d6945b","abstract_canon_sha256":"fde49f6c3236f4c8eda97ee777d1df7870f3096593ccd32cd7fdc785ac4dadb2"},"schema_version":"1.0"},"canonical_sha256":"e1333ffac650d458911c9b149656b11959e3ceff2321143f3750377e2b356819","source":{"kind":"arxiv","id":"2309.04707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04707","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04707v1","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04707","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"4EZT76WGKDKF","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"4EZT76WGKDKFREI4","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"4EZT76WG","created_at":"2026-07-05T06:49:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4EZT76WGKDKFREI4TMKJMVVRDF","target":"record","payload":{"canonical_record":{"source":{"id":"2309.04707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-09T07:19:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25bfd5d0a3e6f7e9d055af383282adabaf0fd864297581d72a50cc9331d6945b","abstract_canon_sha256":"fde49f6c3236f4c8eda97ee777d1df7870f3096593ccd32cd7fdc785ac4dadb2"},"schema_version":"1.0"},"canonical_sha256":"e1333ffac650d458911c9b149656b11959e3ceff2321143f3750377e2b356819","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:07.653112Z","signature_b64":"orksHj1F5eGok4AQWshuhZEBoED7BO/s5R4Si/lzez/FGYYy09NaPfv373K+GCJ6yeNyUL4QZYvXIG4oLhjsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1333ffac650d458911c9b149656b11959e3ceff2321143f3750377e2b356819","last_reissued_at":"2026-07-05T06:49:07.652705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:07.652705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.04707","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":"2026-07-05T06:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJtQS0pmzYV/OZ+XRZyrhjmynSCbMRWwp1b/fphYPlGEuJYBG5nCyXu57rMYsWraBccxPScLgZVyBt6ZbLeXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:27.878340Z"},"content_sha256":"4fcff70c3fdbed622305dd1f6ee37614d48f6295e9d8004bae2b3348c35b6e83","schema_version":"1.0","event_id":"sha256:4fcff70c3fdbed622305dd1f6ee37614d48f6295e9d8004bae2b3348c35b6e83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4EZT76WGKDKFREI4TMKJMVVRDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fang Jin, Feixu Yu, Muzhe Guo, Tian Lan","submitted_at":"2023-09-09T07:19:20Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences. In this paper, we propose a novel Advantage Actor-Critic with Reasoner (A2CR), which can be easily applied to Actor-Critic-based RL models and make them interpretable. A2CR consists of three interconnected networks: the Policy Network, the Value Network, and the Reasoner Network. By predefining and classifying the underlying purpose of the actor's actions, A2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04707","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/2309.04707/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":"2026-07-05T06:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPtyuc+UOYitKquPuVMuj/UM4er45883fhMlhWsyD8F3wdOJWnsPRG3FiBs76tRHeMxd1KJdzWVVyEt4KVWRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:27.878729Z"},"content_sha256":"b6beff39e244ae13a13d5293b4cefc055f7c616d913c209419e243f05e14f018","schema_version":"1.0","event_id":"sha256:b6beff39e244ae13a13d5293b4cefc055f7c616d913c209419e243f05e14f018"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EZT76WGKDKFREI4TMKJMVVRDF/bundle.json","state_url":"https://pith.science/pith/4EZT76WGKDKFREI4TMKJMVVRDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EZT76WGKDKFREI4TMKJMVVRDF/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":"2026-08-06T06:08:27Z","links":{"resolver":"https://pith.science/pith/4EZT76WGKDKFREI4TMKJMVVRDF","bundle":"https://pith.science/pith/4EZT76WGKDKFREI4TMKJMVVRDF/bundle.json","state":"https://pith.science/pith/4EZT76WGKDKFREI4TMKJMVVRDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EZT76WGKDKFREI4TMKJMVVRDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4EZT76WGKDKFREI4TMKJMVVRDF","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":"fde49f6c3236f4c8eda97ee777d1df7870f3096593ccd32cd7fdc785ac4dadb2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-09T07:19:20Z","title_canon_sha256":"25bfd5d0a3e6f7e9d055af383282adabaf0fd864297581d72a50cc9331d6945b"},"schema_version":"1.0","source":{"id":"2309.04707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04707","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04707v1","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04707","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"4EZT76WGKDKF","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"4EZT76WGKDKFREI4","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"4EZT76WG","created_at":"2026-07-05T06:49:07Z"}],"graph_snapshots":[{"event_id":"sha256:b6beff39e244ae13a13d5293b4cefc055f7c616d913c209419e243f05e14f018","target":"graph","created_at":"2026-07-05T06:49:07Z","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/2309.04707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences. In this paper, we propose a novel Advantage Actor-Critic with Reasoner (A2CR), which can be easily applied to Actor-Critic-based RL models and make them interpretable. A2CR consists of three interconnected networks: the Policy Network, the Value Network, and the Reasoner Network. By predefining and classifying the underlying purpose of the actor's actions, A2","authors_text":"Fang Jin, Feixu Yu, Muzhe Guo, Tian Lan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-09T07:19:20Z","title":"Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04707","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":"sha256:4fcff70c3fdbed622305dd1f6ee37614d48f6295e9d8004bae2b3348c35b6e83","target":"record","created_at":"2026-07-05T06:49:07Z","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":"fde49f6c3236f4c8eda97ee777d1df7870f3096593ccd32cd7fdc785ac4dadb2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-09T07:19:20Z","title_canon_sha256":"25bfd5d0a3e6f7e9d055af383282adabaf0fd864297581d72a50cc9331d6945b"},"schema_version":"1.0","source":{"id":"2309.04707","kind":"arxiv","version":1}},"canonical_sha256":"e1333ffac650d458911c9b149656b11959e3ceff2321143f3750377e2b356819","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1333ffac650d458911c9b149656b11959e3ceff2321143f3750377e2b356819","first_computed_at":"2026-07-05T06:49:07.652705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:07.652705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"orksHj1F5eGok4AQWshuhZEBoED7BO/s5R4Si/lzez/FGYYy09NaPfv373K+GCJ6yeNyUL4QZYvXIG4oLhjsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:07.653112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fcff70c3fdbed622305dd1f6ee37614d48f6295e9d8004bae2b3348c35b6e83","sha256:b6beff39e244ae13a13d5293b4cefc055f7c616d913c209419e243f05e14f018"],"state_sha256":"4cb4b1e0d4c8f2cf292b0f409c384150669cf7e52150017f4b24ea97b4e65411"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOFXpWyG+/iahHugUbDn4rxsKbgu0lalKCVIajH9sMb5G6keewpQ/LeJTMT840PVV6inuKHDxoZlZwIZVgnnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:08:27.882733Z","bundle_sha256":"c5c92deec77dcf736daffd0df4d27344eebd48fc56eb1dcc0f5695a6c1498912"}}