{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KP6EGVPA6F5UBH6473RRXPREIP","short_pith_number":"pith:KP6EGVPA","canonical_record":{"source":{"id":"2309.01458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T09:09:54Z","cross_cats_sorted":[],"title_canon_sha256":"2e0e4f512aa8cbad6d0fbe19a55be92423afd81d4bc6b465bed9b705fbb4cf65","abstract_canon_sha256":"b257ffe8b701c13201a01f099816cf8aa4e26b6f58a2b24baf250fc8fcd6b5ca"},"schema_version":"1.0"},"canonical_sha256":"53fc4355e0f17b409fdcfee31bbe2443dc3dbf71c320961d26de8aac02a91402","source":{"kind":"arxiv","id":"2309.01458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01458","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01458v1","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01458","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"KP6EGVPA6F5U","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"KP6EGVPA6F5UBH64","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"KP6EGVPA","created_at":"2026-07-05T06:47:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KP6EGVPA6F5UBH6473RRXPREIP","target":"record","payload":{"canonical_record":{"source":{"id":"2309.01458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T09:09:54Z","cross_cats_sorted":[],"title_canon_sha256":"2e0e4f512aa8cbad6d0fbe19a55be92423afd81d4bc6b465bed9b705fbb4cf65","abstract_canon_sha256":"b257ffe8b701c13201a01f099816cf8aa4e26b6f58a2b24baf250fc8fcd6b5ca"},"schema_version":"1.0"},"canonical_sha256":"53fc4355e0f17b409fdcfee31bbe2443dc3dbf71c320961d26de8aac02a91402","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:38.215354Z","signature_b64":"v/bxhHjNdJQY5tm5viHhQZNwE8XnHgbA7LqQxnYxtshuNgyccvCrEJB+vNyWPIJ85pCrEJsb91WEILIeBhY/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53fc4355e0f17b409fdcfee31bbe2443dc3dbf71c320961d26de8aac02a91402","last_reissued_at":"2026-07-05T06:47:38.214914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:38.214914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.01458","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":"2026-07-05T06:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xks8GrAVQOCWPXTiGFDIa+lZJs4pJLxnlnf/OREx6p0HbqbcdywkpttHN9mMshH/hhrgxv/+F4x67uU3hGkuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:44:20.512709Z"},"content_sha256":"903308df45dee2201fea6d29a71136c8fa3cadaaa249a35b310a2c02fc708a95","schema_version":"1.0","event_id":"sha256:903308df45dee2201fea6d29a71136c8fa3cadaaa249a35b310a2c02fc708a95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KP6EGVPA6F5UBH6473RRXPREIP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gao Huang, Huanqian Wang, Mukun Tong, Qisen Yang, Shiji Song, Wenjie Shi","submitted_at":"2023-09-04T09:09:54Z","abstract_excerpt":"The black-box nature of deep reinforcement learning (RL) hinders them from real-world applications. Therefore, interpreting and explaining RL agents have been active research topics in recent years. Existing methods for post-hoc explanations usually adopt the action matching principle to enable an easy understanding of vision-based RL agents. In this paper, it is argued that the commonly used action matching principle is more like an explanation of deep neural networks (DNNs) than the interpretation of RL agents. It may lead to irrelevant or misplaced feature attribution when different DNNs' o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01458","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/2309.01458/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":"2026-07-05T06:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfZwDi4R/Fmvwz2v08dXbDnaszk6MJ4E1K5pk/zjTLYM0okdd9ehCr2ZIoOuxjmxnujjhEpQ0Ed9kfzCahTpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:44:20.513075Z"},"content_sha256":"981b48d4fc661f867bba1d37aa7a3e1b8fd5411d859c4296f4246caa1fc372ec","schema_version":"1.0","event_id":"sha256:981b48d4fc661f867bba1d37aa7a3e1b8fd5411d859c4296f4246caa1fc372ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KP6EGVPA6F5UBH6473RRXPREIP/bundle.json","state_url":"https://pith.science/pith/KP6EGVPA6F5UBH6473RRXPREIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KP6EGVPA6F5UBH6473RRXPREIP/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":"2026-07-17T15:44:20Z","links":{"resolver":"https://pith.science/pith/KP6EGVPA6F5UBH6473RRXPREIP","bundle":"https://pith.science/pith/KP6EGVPA6F5UBH6473RRXPREIP/bundle.json","state":"https://pith.science/pith/KP6EGVPA6F5UBH6473RRXPREIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KP6EGVPA6F5UBH6473RRXPREIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KP6EGVPA6F5UBH6473RRXPREIP","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":"b257ffe8b701c13201a01f099816cf8aa4e26b6f58a2b24baf250fc8fcd6b5ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T09:09:54Z","title_canon_sha256":"2e0e4f512aa8cbad6d0fbe19a55be92423afd81d4bc6b465bed9b705fbb4cf65"},"schema_version":"1.0","source":{"id":"2309.01458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01458","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01458v1","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01458","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"KP6EGVPA6F5U","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"KP6EGVPA6F5UBH64","created_at":"2026-07-05T06:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"KP6EGVPA","created_at":"2026-07-05T06:47:38Z"}],"graph_snapshots":[{"event_id":"sha256:981b48d4fc661f867bba1d37aa7a3e1b8fd5411d859c4296f4246caa1fc372ec","target":"graph","created_at":"2026-07-05T06:47:38Z","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/2309.01458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The black-box nature of deep reinforcement learning (RL) hinders them from real-world applications. Therefore, interpreting and explaining RL agents have been active research topics in recent years. Existing methods for post-hoc explanations usually adopt the action matching principle to enable an easy understanding of vision-based RL agents. In this paper, it is argued that the commonly used action matching principle is more like an explanation of deep neural networks (DNNs) than the interpretation of RL agents. It may lead to irrelevant or misplaced feature attribution when different DNNs' o","authors_text":"Gao Huang, Huanqian Wang, Mukun Tong, Qisen Yang, Shiji Song, Wenjie Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T09:09:54Z","title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01458","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":"sha256:903308df45dee2201fea6d29a71136c8fa3cadaaa249a35b310a2c02fc708a95","target":"record","created_at":"2026-07-05T06:47:38Z","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":"b257ffe8b701c13201a01f099816cf8aa4e26b6f58a2b24baf250fc8fcd6b5ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T09:09:54Z","title_canon_sha256":"2e0e4f512aa8cbad6d0fbe19a55be92423afd81d4bc6b465bed9b705fbb4cf65"},"schema_version":"1.0","source":{"id":"2309.01458","kind":"arxiv","version":1}},"canonical_sha256":"53fc4355e0f17b409fdcfee31bbe2443dc3dbf71c320961d26de8aac02a91402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53fc4355e0f17b409fdcfee31bbe2443dc3dbf71c320961d26de8aac02a91402","first_computed_at":"2026-07-05T06:47:38.214914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:38.214914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/bxhHjNdJQY5tm5viHhQZNwE8XnHgbA7LqQxnYxtshuNgyccvCrEJB+vNyWPIJ85pCrEJsb91WEILIeBhY/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:38.215354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:903308df45dee2201fea6d29a71136c8fa3cadaaa249a35b310a2c02fc708a95","sha256:981b48d4fc661f867bba1d37aa7a3e1b8fd5411d859c4296f4246caa1fc372ec"],"state_sha256":"1e31de55597423552d87f53f8c61f90faf7ce0ab2b71dbf8e542fb07e9865f1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngYzkcUO9sfg5tlq6FBlOp41GKWk4MwOYT+3YIEK2V9Oyj44HkblKWcbS3Zs29FNJKivF1/HcjHZJcjM3D8UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T15:44:20.515152Z","bundle_sha256":"5ee092801110ad8d62611d1cfff17dd4ec07af28b33752f1c4b7af70276c390a"}}