{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R7YF3H2AV5VYOI74DJI6TZ6YMR","short_pith_number":"pith:R7YF3H2A","canonical_record":{"source":{"id":"1906.00088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T21:29:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"caed4400cdb887c5ef00cdbda05e2bcc11dfd72f2b47ccc718af50648f75a7c1","abstract_canon_sha256":"4b623df2f147b4f43e9382ab78faba2acf015ae2cd6b28e76c6dbfcb7f16bb7a"},"schema_version":"1.0"},"canonical_sha256":"8ff05d9f40af6b8723fc1a51e9e7d864770642452172ad443ab421914c59312d","source":{"kind":"arxiv","id":"1906.00088","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00088","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00088v1","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00088","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"pith_short_12","alias_value":"R7YF3H2AV5VY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R7YF3H2AV5VYOI74","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R7YF3H2A","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R7YF3H2AV5VYOI74DJI6TZ6YMR","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T21:29:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"caed4400cdb887c5ef00cdbda05e2bcc11dfd72f2b47ccc718af50648f75a7c1","abstract_canon_sha256":"4b623df2f147b4f43e9382ab78faba2acf015ae2cd6b28e76c6dbfcb7f16bb7a"},"schema_version":"1.0"},"canonical_sha256":"8ff05d9f40af6b8723fc1a51e9e7d864770642452172ad443ab421914c59312d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:33.497978Z","signature_b64":"1I7QkBdkUO0xCWG4Z/ex78xDirlfN6S9bSoDvQg3aHXUjYnocTyhC7Zg4q2SUhrHfaz+olK+AFYXMNUTI1S9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ff05d9f40af6b8723fc1a51e9e7d864770642452172ad443ab421914c59312d","last_reissued_at":"2026-05-17T23:44:33.497478Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:33.497478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00088","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":"2026-05-17T23:44:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRRS2zoTHGMuJDJFnmQG0PAj6fKVNitR5MIjZ9M1ptdn9qZfLMHAjCIg+7faIt8t4+vURcU+F1wo+Is1E6RXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:12:38.339381Z"},"content_sha256":"2915c3f7ef9f577575b66687730f6d2050b72cba2e46106326f2fd1ca46cbe6b","schema_version":"1.0","event_id":"sha256:2915c3f7ef9f577575b66687730f6d2050b72cba2e46106326f2fd1ca46cbe6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R7YF3H2AV5VYOI74DJI6TZ6YMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Finale Doshi-Velez, Muhammad A. Masood","submitted_at":"2019-05-31T21:29:25Z","abstract_excerpt":"Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently explore the space of reasonable solutions. Unfortunately, existing approaches that quantify uncertainty over policies are not ultimately relevant to finding policies with qualitatively distinct behaviors. In this work, we formalize the difference between policies as a difference between the distribution of trajectories induced by each policy, which encourag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00088","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84X7TVml8XEEzYjPJcL3hjeUE0WKSZeHIYVaoqXBQDb6HSrNUhPbcMcpv9YAIJymfwvWHjk45w2tdi4VPJhzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:12:38.339741Z"},"content_sha256":"e553d987a8373e50ee59b3873480ff7ef495256352f3de602e0a2c955acf1fcb","schema_version":"1.0","event_id":"sha256:e553d987a8373e50ee59b3873480ff7ef495256352f3de602e0a2c955acf1fcb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/bundle.json","state_url":"https://pith.science/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/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":"2026-06-02T19:12:38Z","links":{"resolver":"https://pith.science/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR","bundle":"https://pith.science/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/bundle.json","state":"https://pith.science/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7YF3H2AV5VYOI74DJI6TZ6YMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R7YF3H2AV5VYOI74DJI6TZ6YMR","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":"4b623df2f147b4f43e9382ab78faba2acf015ae2cd6b28e76c6dbfcb7f16bb7a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T21:29:25Z","title_canon_sha256":"caed4400cdb887c5ef00cdbda05e2bcc11dfd72f2b47ccc718af50648f75a7c1"},"schema_version":"1.0","source":{"id":"1906.00088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00088","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00088v1","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00088","created_at":"2026-05-17T23:44:33Z"},{"alias_kind":"pith_short_12","alias_value":"R7YF3H2AV5VY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R7YF3H2AV5VYOI74","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R7YF3H2A","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:e553d987a8373e50ee59b3873480ff7ef495256352f3de602e0a2c955acf1fcb","target":"graph","created_at":"2026-05-17T23:44:33Z","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"},"paper":{"abstract_excerpt":"Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently explore the space of reasonable solutions. Unfortunately, existing approaches that quantify uncertainty over policies are not ultimately relevant to finding policies with qualitatively distinct behaviors. In this work, we formalize the difference between policies as a difference between the distribution of trajectories induced by each policy, which encourag","authors_text":"Finale Doshi-Velez, Muhammad A. Masood","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T21:29:25Z","title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00088","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":"sha256:2915c3f7ef9f577575b66687730f6d2050b72cba2e46106326f2fd1ca46cbe6b","target":"record","created_at":"2026-05-17T23:44:33Z","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":"4b623df2f147b4f43e9382ab78faba2acf015ae2cd6b28e76c6dbfcb7f16bb7a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T21:29:25Z","title_canon_sha256":"caed4400cdb887c5ef00cdbda05e2bcc11dfd72f2b47ccc718af50648f75a7c1"},"schema_version":"1.0","source":{"id":"1906.00088","kind":"arxiv","version":1}},"canonical_sha256":"8ff05d9f40af6b8723fc1a51e9e7d864770642452172ad443ab421914c59312d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ff05d9f40af6b8723fc1a51e9e7d864770642452172ad443ab421914c59312d","first_computed_at":"2026-05-17T23:44:33.497478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:33.497478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1I7QkBdkUO0xCWG4Z/ex78xDirlfN6S9bSoDvQg3aHXUjYnocTyhC7Zg4q2SUhrHfaz+olK+AFYXMNUTI1S9Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:33.497978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2915c3f7ef9f577575b66687730f6d2050b72cba2e46106326f2fd1ca46cbe6b","sha256:e553d987a8373e50ee59b3873480ff7ef495256352f3de602e0a2c955acf1fcb"],"state_sha256":"cea13e414b7a646d58c0cc9f9076112619a8cef285f43c63974e9c24b77b953d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0v+W3y6Ysti3Ln0u7TGU5t17Ga1ezhiqMlfk/Mw7PVnsZtykRWby5NZ+b5hXzhC+PlLBUj0Hjix7nXwNe0RiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:12:38.341890Z","bundle_sha256":"f2b0b458afda0acd329f5e76f51be92ce00a9c53edfbd4e0785c8893c35faac1"}}