{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IHDA6NLVNNYYEYLWYKJT64272M","short_pith_number":"pith:IHDA6NLV","canonical_record":{"source":{"id":"1811.09013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"048f4a0ba38dc33d23ef88b4261d66fec4c91ab89a0846c8a9383083f542d787","abstract_canon_sha256":"2b52702fdcb2c26169ce6e5b45fd441ea24bcd2d5d07845be42f572d2ccc99ec"},"schema_version":"1.0"},"canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","source":{"kind":"arxiv","id":"1811.09013","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09013","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09013v2","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09013","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"IHDA6NLVNNYY","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IHDA6NLVNNYYEYLW","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IHDA6NLV","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IHDA6NLVNNYYEYLWYKJT64272M","target":"record","payload":{"canonical_record":{"source":{"id":"1811.09013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"048f4a0ba38dc33d23ef88b4261d66fec4c91ab89a0846c8a9383083f542d787","abstract_canon_sha256":"2b52702fdcb2c26169ce6e5b45fd441ea24bcd2d5d07845be42f572d2ccc99ec"},"schema_version":"1.0"},"canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:53.576301Z","signature_b64":"cM3+/PZzj0xrhdWsihCWyaY/ngFTJup5HuRjCxIEdSTyvKA+3UeOWI8bH4YIy6MFo0uvRye9RcitlFFKPUuSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","last_reissued_at":"2026-05-17T23:42:53.575820Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:53.575820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.09013","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":"2026-05-17T23:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anqHKNL8JQDhXagt/Tih5VWpJ03BjcXpuhL6NVENddZTRnD3MmHQf1Cpm+4diw9NjeEeJPMLY9Q0R5vfHqhLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T08:20:56.920990Z"},"content_sha256":"d335a5ced6a78d9230b01217111d48fc81cf5e228a5efaa02231d99b1720f8db","schema_version":"1.0","event_id":"sha256:d335a5ced6a78d9230b01217111d48fc81cf5e228a5efaa02231d99b1720f8db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IHDA6NLVNNYYEYLWYKJT64272M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ehsan Imani, Eric Graves, Martha White","submitted_at":"2018-11-22T03:58:11Z","abstract_excerpt":"Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient. In off-policy learning, however, where the behaviour policy is not necessarily attempting to learn and follow the optimal policy for the given task, the existence of such a theorem has been elusive. In this work, we solve this open problem by providing the first off-policy pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09013","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":""},"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":"2026-05-17T23:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rnv95fk6mSzcJzQYE+VwkYM0DpiHnXPA6tF2+4hd7S+0cKhiDfm0+xCifB/6iiN4pCx5vY8tw/NIQJUjk67SBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T08:20:56.921620Z"},"content_sha256":"fdfd88dafe520b014a68c8cd4c1b27ebf8ae0fd8b77961623b2a196e8fca5eb6","schema_version":"1.0","event_id":"sha256:fdfd88dafe520b014a68c8cd4c1b27ebf8ae0fd8b77961623b2a196e8fca5eb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/bundle.json","state_url":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IHDA6NLVNNYYEYLWYKJT64272M/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":"2026-06-08T08:20:56Z","links":{"resolver":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M","bundle":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/bundle.json","state":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IHDA6NLVNNYYEYLWYKJT64272M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IHDA6NLVNNYYEYLWYKJT64272M","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":"2b52702fdcb2c26169ce6e5b45fd441ea24bcd2d5d07845be42f572d2ccc99ec","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","title_canon_sha256":"048f4a0ba38dc33d23ef88b4261d66fec4c91ab89a0846c8a9383083f542d787"},"schema_version":"1.0","source":{"id":"1811.09013","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09013","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09013v2","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09013","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"IHDA6NLVNNYY","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IHDA6NLVNNYYEYLW","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IHDA6NLV","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:fdfd88dafe520b014a68c8cd4c1b27ebf8ae0fd8b77961623b2a196e8fca5eb6","target":"graph","created_at":"2026-05-17T23:42:53Z","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":"Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient. In off-policy learning, however, where the behaviour policy is not necessarily attempting to learn and follow the optimal policy for the given task, the existence of such a theorem has been elusive. In this work, we solve this open problem by providing the first off-policy pol","authors_text":"Ehsan Imani, Eric Graves, Martha White","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09013","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:d335a5ced6a78d9230b01217111d48fc81cf5e228a5efaa02231d99b1720f8db","target":"record","created_at":"2026-05-17T23:42:53Z","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":"2b52702fdcb2c26169ce6e5b45fd441ea24bcd2d5d07845be42f572d2ccc99ec","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","title_canon_sha256":"048f4a0ba38dc33d23ef88b4261d66fec4c91ab89a0846c8a9383083f542d787"},"schema_version":"1.0","source":{"id":"1811.09013","kind":"arxiv","version":2}},"canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","first_computed_at":"2026-05-17T23:42:53.575820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:53.575820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cM3+/PZzj0xrhdWsihCWyaY/ngFTJup5HuRjCxIEdSTyvKA+3UeOWI8bH4YIy6MFo0uvRye9RcitlFFKPUuSBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:53.576301Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.09013","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d335a5ced6a78d9230b01217111d48fc81cf5e228a5efaa02231d99b1720f8db","sha256:fdfd88dafe520b014a68c8cd4c1b27ebf8ae0fd8b77961623b2a196e8fca5eb6"],"state_sha256":"e8f5fb665e670c96b0c2d4811a66ec14f5d2266025aeb0ba6048b2b89bb5c2c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EnpKzQaDxp9zFtLBHCfZRTasNfJ5z/A0rfP/qAgcaPB1IPH4VEIydXUjw/qOcI4QtdmuL0z+KTZsnChh+T+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T08:20:56.926132Z","bundle_sha256":"dede3a7743b99a0af7bc6b8f12e2556fdb752b32a005aa5baec9ff1da90e67ad"}}