{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VAMX25I36XMTF3O3JMIDW46Y2F","short_pith_number":"pith:VAMX25I3","canonical_record":{"source":{"id":"2112.13112","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T17:26:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a95ba0419d9c56e3326ba10781d635a37573fcd0f1edeb44ded9dd3fa6ff9dba","abstract_canon_sha256":"bca73cae3aeb3e66ba9825f03c978e2a2b569770bae0af0b17dbb3a3a691fa19"},"schema_version":"1.0"},"canonical_sha256":"a8197d751bf5d932eddb4b103b73d8d16523f9768a531e6f5056517366947930","source":{"kind":"arxiv","id":"2112.13112","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13112","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13112v2","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13112","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"VAMX25I36XMT","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"VAMX25I36XMTF3O3","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"VAMX25I3","created_at":"2026-07-05T03:59:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VAMX25I36XMTF3O3JMIDW46Y2F","target":"record","payload":{"canonical_record":{"source":{"id":"2112.13112","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T17:26:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a95ba0419d9c56e3326ba10781d635a37573fcd0f1edeb44ded9dd3fa6ff9dba","abstract_canon_sha256":"bca73cae3aeb3e66ba9825f03c978e2a2b569770bae0af0b17dbb3a3a691fa19"},"schema_version":"1.0"},"canonical_sha256":"a8197d751bf5d932eddb4b103b73d8d16523f9768a531e6f5056517366947930","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:43.469026Z","signature_b64":"6l4m/A2kRwAqomSckdbIjzvrFL79/J76J/o39ZOzsnA2yprCt5mBZxo0bbWTyhSGR69xdZoS/9vaSQdmt9EkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8197d751bf5d932eddb4b103b73d8d16523f9768a531e6f5056517366947930","last_reissued_at":"2026-07-05T03:59:43.468562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:43.468562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.13112","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:59:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCwk1qsjGL7Rij6C3HXGFSvN7PmlPR5AWgRVtfM3skmutCSSM1UK2WlEsEZDsLdW7ZsqYau5iQFARj1JGhkMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:36:33.558301Z"},"content_sha256":"f8d6b77fba1b63231cae755a92382a91fdcc30ef4724b6c666edd6270b9f47bc","schema_version":"1.0","event_id":"sha256:f8d6b77fba1b63231cae755a92382a91fdcc30ef4724b6c666edd6270b9f47bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VAMX25I36XMTF3O3JMIDW46Y2F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Interpretable Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Claire Glanois, Dong Li, Jianye Hao, Matthieu Zimmer, Paul Weng, Tianpei Yang, Wulong Liu","submitted_at":"2021-12-24T17:26:57Z","abstract_excerpt":"Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13112","kind":"arxiv","version":2},"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/2112.13112/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":"2026-07-05T03:59:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92BraZBcL6y+RCZCokWuxtSBgf5Q/cY09Bf9Qs0p8X1JOznUUd1LbPzz7xtkAf+RECyPmfwzkW5UH10st6c9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:36:33.558688Z"},"content_sha256":"2d865c5dbfb232f09f37f82e52d57dfcd01c04621d4d7dc17531cdd94eec98d3","schema_version":"1.0","event_id":"sha256:2d865c5dbfb232f09f37f82e52d57dfcd01c04621d4d7dc17531cdd94eec98d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VAMX25I36XMTF3O3JMIDW46Y2F/bundle.json","state_url":"https://pith.science/pith/VAMX25I36XMTF3O3JMIDW46Y2F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VAMX25I36XMTF3O3JMIDW46Y2F/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":"2026-07-11T21:36:33Z","links":{"resolver":"https://pith.science/pith/VAMX25I36XMTF3O3JMIDW46Y2F","bundle":"https://pith.science/pith/VAMX25I36XMTF3O3JMIDW46Y2F/bundle.json","state":"https://pith.science/pith/VAMX25I36XMTF3O3JMIDW46Y2F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VAMX25I36XMTF3O3JMIDW46Y2F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VAMX25I36XMTF3O3JMIDW46Y2F","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":"bca73cae3aeb3e66ba9825f03c978e2a2b569770bae0af0b17dbb3a3a691fa19","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T17:26:57Z","title_canon_sha256":"a95ba0419d9c56e3326ba10781d635a37573fcd0f1edeb44ded9dd3fa6ff9dba"},"schema_version":"1.0","source":{"id":"2112.13112","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13112","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13112v2","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13112","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"VAMX25I36XMT","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"VAMX25I36XMTF3O3","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"VAMX25I3","created_at":"2026-07-05T03:59:43Z"}],"graph_snapshots":[{"event_id":"sha256:2d865c5dbfb232f09f37f82e52d57dfcd01c04621d4d7dc17531cdd94eec98d3","target":"graph","created_at":"2026-07-05T03:59:43Z","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/2112.13112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and","authors_text":"Claire Glanois, Dong Li, Jianye Hao, Matthieu Zimmer, Paul Weng, Tianpei Yang, Wulong Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T17:26:57Z","title":"A Survey on Interpretable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13112","kind":"arxiv","version":2},"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:f8d6b77fba1b63231cae755a92382a91fdcc30ef4724b6c666edd6270b9f47bc","target":"record","created_at":"2026-07-05T03:59:43Z","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":"bca73cae3aeb3e66ba9825f03c978e2a2b569770bae0af0b17dbb3a3a691fa19","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T17:26:57Z","title_canon_sha256":"a95ba0419d9c56e3326ba10781d635a37573fcd0f1edeb44ded9dd3fa6ff9dba"},"schema_version":"1.0","source":{"id":"2112.13112","kind":"arxiv","version":2}},"canonical_sha256":"a8197d751bf5d932eddb4b103b73d8d16523f9768a531e6f5056517366947930","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8197d751bf5d932eddb4b103b73d8d16523f9768a531e6f5056517366947930","first_computed_at":"2026-07-05T03:59:43.468562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:43.468562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6l4m/A2kRwAqomSckdbIjzvrFL79/J76J/o39ZOzsnA2yprCt5mBZxo0bbWTyhSGR69xdZoS/9vaSQdmt9EkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:43.469026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13112","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8d6b77fba1b63231cae755a92382a91fdcc30ef4724b6c666edd6270b9f47bc","sha256:2d865c5dbfb232f09f37f82e52d57dfcd01c04621d4d7dc17531cdd94eec98d3"],"state_sha256":"a2c9a10899e76acaab840cb4db31cfb0d69ca22f4b875c20128099a61cf09891"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+pLwCdiPjqcuDNeFgAAmxh/W8qVqDN+SvoOGqvqRimyST47tUNTDC33ZGrTMsV35gMY3sTRHBQkKR2TItu4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T21:36:33.560782Z","bundle_sha256":"f1b07469d09fea2c46863e339d7c7d309d19059242ed3d985ad13a0de588b1fd"}}