{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZFQN5GPFYSBCZDQ2GU2ELIP65F","short_pith_number":"pith:ZFQN5GPF","schema_version":"1.0","canonical_sha256":"c960de99e5c4822c8e1a353445a1fee975cc60a46280a8c040860a4f467e34b5","source":{"kind":"arxiv","id":"1905.12044","version":1},"attestation_state":"computed","paper":{"title":"Generation of Policy-Level Explanations for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Manuela Veloso, Nicholay Topin","submitted_at":"2019-05-28T19:33:49Z","abstract_excerpt":"Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current work in explainable deep learning focuses on explaining only a single decision in terms of input features, making it unsuitable for explaining a sequence of decisions. To address this need, we introduce Abstracted Policy Graphs, which are Markov chains of abstract states. This representation concisely summarizes a policy so that individual decisions can be explained in the context of expected future transitions. Additio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.12044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:33:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"00af7d07fa030c05928d02a9eec2ff99de28b45a9ea76ba6710385ca6dabd152","abstract_canon_sha256":"85d58eecb6b3c72dcb29458f3c876ac4b069c000473d8d671275865a21d4e6cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:49.118374Z","signature_b64":"59CZN4bMJHV7dMUnePm1pNCTPU6D1O6t9CPhP8g1RER44ZttF+9PhQpkRhAEQ6m80Etj+m5iv/PXPqjaGMWtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c960de99e5c4822c8e1a353445a1fee975cc60a46280a8c040860a4f467e34b5","last_reissued_at":"2026-05-17T23:44:49.117763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:49.117763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generation of Policy-Level Explanations for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Manuela Veloso, Nicholay Topin","submitted_at":"2019-05-28T19:33:49Z","abstract_excerpt":"Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current work in explainable deep learning focuses on explaining only a single decision in terms of input features, making it unsuitable for explaining a sequence of decisions. To address this need, we introduce Abstracted Policy Graphs, which are Markov chains of abstract states. This representation concisely summarizes a policy so that individual decisions can be explained in the context of expected future transitions. Additio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12044","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.12044","created_at":"2026-05-17T23:44:49.117858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12044v1","created_at":"2026-05-17T23:44:49.117858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12044","created_at":"2026-05-17T23:44:49.117858+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFQN5GPFYSBC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFQN5GPFYSBCZDQ2","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFQN5GPF","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F","json":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F.json","graph_json":"https://pith.science/api/pith-number/ZFQN5GPFYSBCZDQ2GU2ELIP65F/graph.json","events_json":"https://pith.science/api/pith-number/ZFQN5GPFYSBCZDQ2GU2ELIP65F/events.json","paper":"https://pith.science/paper/ZFQN5GPF"},"agent_actions":{"view_html":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F","download_json":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F.json","view_paper":"https://pith.science/paper/ZFQN5GPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12044&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFQN5GPFYSBCZDQ2GU2ELIP65F/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFQN5GPFYSBCZDQ2GU2ELIP65F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F/action/storage_attestation","attest_author":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F/action/author_attestation","sign_citation":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F/action/citation_signature","submit_replication":"https://pith.science/pith/ZFQN5GPFYSBCZDQ2GU2ELIP65F/action/replication_record"}},"created_at":"2026-05-17T23:44:49.117858+00:00","updated_at":"2026-05-17T23:44:49.117858+00:00"}