{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UUVXJNB7V366YJNST42FI6DBEU","short_pith_number":"pith:UUVXJNB7","canonical_record":{"source":{"id":"2111.08172","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T01:18:16Z","cross_cats_sorted":[],"title_canon_sha256":"d73c40bb840c0f67fbfe6255dd285f9ba14236be36e759e8e8c0c075d486c869","abstract_canon_sha256":"a47fd775c74524a19a6ca99643c8d20f26be6dde1242087e300a9f78d1f67657"},"schema_version":"1.0"},"canonical_sha256":"a52b74b43faefdec25b29f34547861253e2871a3ba240b3fefe0cfd467b0bd1f","source":{"kind":"arxiv","id":"2111.08172","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08172","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08172v3","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08172","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_12","alias_value":"UUVXJNB7V366","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_16","alias_value":"UUVXJNB7V366YJNS","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_8","alias_value":"UUVXJNB7","created_at":"2026-07-05T06:00:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UUVXJNB7V366YJNST42FI6DBEU","target":"record","payload":{"canonical_record":{"source":{"id":"2111.08172","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T01:18:16Z","cross_cats_sorted":[],"title_canon_sha256":"d73c40bb840c0f67fbfe6255dd285f9ba14236be36e759e8e8c0c075d486c869","abstract_canon_sha256":"a47fd775c74524a19a6ca99643c8d20f26be6dde1242087e300a9f78d1f67657"},"schema_version":"1.0"},"canonical_sha256":"a52b74b43faefdec25b29f34547861253e2871a3ba240b3fefe0cfd467b0bd1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:54.895091Z","signature_b64":"3h3zi87ChFaF3oxsWT8td7evCnQcqckNZOmrGiYMFnCKB71z+UMiJVrtyvKj892JkA4N/ZwRgVcoLxq8pFOOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a52b74b43faefdec25b29f34547861253e2871a3ba240b3fefe0cfd467b0bd1f","last_reissued_at":"2026-07-05T06:00:54.894753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:54.894753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.08172","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:00:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgtfGbRNGKQGAWPa5fyyhyalNv5e0b5toL/Pp0r+w30iIxQM3nrBmi3GIf1s0egH6volip4BPwyPKfz2WXXZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:27.640257Z"},"content_sha256":"dce08c48758c08c49ee4345067bc2acd0d36c2103d768f1c14955c66cf08fe24","schema_version":"1.0","event_id":"sha256:dce08c48758c08c49ee4345067bc2acd0d36c2103d768f1c14955c66cf08fe24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UUVXJNB7V366YJNST42FI6DBEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Actor-Critic with Emphatic Weightings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ehsan Imani, Eric Graves, Martha White, Raksha Kumaraswamy","submitted_at":"2021-11-16T01:18:16Z","abstract_excerpt":"A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to the existence of multiple objectives and the lack of an explicit off-policy policy gradient theorem. In this work, we unify these objectives into one off-policy objective, and provide a policy gradient theorem for this unified objective. The derivation involves emphatic weightings and interest functions. We show multiple strategies to approximate the gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08172","kind":"arxiv","version":3},"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/2111.08172/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":"2026-07-05T06:00:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UxqV1AUUiRJmHrIrvxYw6oNxXvBqgUOZCQ4IhEA24VAof1ZGRmuSy8z133FWGx1OlwXCP6wtOe1ZRBiykqWWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:27.641058Z"},"content_sha256":"b5da1faba4c8fd1e5b8a998231e2bc450147adb94c574f4d617511ebb2247729","schema_version":"1.0","event_id":"sha256:b5da1faba4c8fd1e5b8a998231e2bc450147adb94c574f4d617511ebb2247729"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUVXJNB7V366YJNST42FI6DBEU/bundle.json","state_url":"https://pith.science/pith/UUVXJNB7V366YJNST42FI6DBEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUVXJNB7V366YJNST42FI6DBEU/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":"2026-08-07T03:38:27Z","links":{"resolver":"https://pith.science/pith/UUVXJNB7V366YJNST42FI6DBEU","bundle":"https://pith.science/pith/UUVXJNB7V366YJNST42FI6DBEU/bundle.json","state":"https://pith.science/pith/UUVXJNB7V366YJNST42FI6DBEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUVXJNB7V366YJNST42FI6DBEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UUVXJNB7V366YJNST42FI6DBEU","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":"a47fd775c74524a19a6ca99643c8d20f26be6dde1242087e300a9f78d1f67657","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T01:18:16Z","title_canon_sha256":"d73c40bb840c0f67fbfe6255dd285f9ba14236be36e759e8e8c0c075d486c869"},"schema_version":"1.0","source":{"id":"2111.08172","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08172","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08172v3","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08172","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_12","alias_value":"UUVXJNB7V366","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_16","alias_value":"UUVXJNB7V366YJNS","created_at":"2026-07-05T06:00:54Z"},{"alias_kind":"pith_short_8","alias_value":"UUVXJNB7","created_at":"2026-07-05T06:00:54Z"}],"graph_snapshots":[{"event_id":"sha256:b5da1faba4c8fd1e5b8a998231e2bc450147adb94c574f4d617511ebb2247729","target":"graph","created_at":"2026-07-05T06:00:54Z","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/2111.08172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to the existence of multiple objectives and the lack of an explicit off-policy policy gradient theorem. In this work, we unify these objectives into one off-policy objective, and provide a policy gradient theorem for this unified objective. The derivation involves emphatic weightings and interest functions. We show multiple strategies to approximate the gradient","authors_text":"Ehsan Imani, Eric Graves, Martha White, Raksha Kumaraswamy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T01:18:16Z","title":"Off-Policy Actor-Critic with Emphatic Weightings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08172","kind":"arxiv","version":3},"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:dce08c48758c08c49ee4345067bc2acd0d36c2103d768f1c14955c66cf08fe24","target":"record","created_at":"2026-07-05T06:00:54Z","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":"a47fd775c74524a19a6ca99643c8d20f26be6dde1242087e300a9f78d1f67657","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T01:18:16Z","title_canon_sha256":"d73c40bb840c0f67fbfe6255dd285f9ba14236be36e759e8e8c0c075d486c869"},"schema_version":"1.0","source":{"id":"2111.08172","kind":"arxiv","version":3}},"canonical_sha256":"a52b74b43faefdec25b29f34547861253e2871a3ba240b3fefe0cfd467b0bd1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a52b74b43faefdec25b29f34547861253e2871a3ba240b3fefe0cfd467b0bd1f","first_computed_at":"2026-07-05T06:00:54.894753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:54.894753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3h3zi87ChFaF3oxsWT8td7evCnQcqckNZOmrGiYMFnCKB71z+UMiJVrtyvKj892JkA4N/ZwRgVcoLxq8pFOOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:54.895091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08172","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dce08c48758c08c49ee4345067bc2acd0d36c2103d768f1c14955c66cf08fe24","sha256:b5da1faba4c8fd1e5b8a998231e2bc450147adb94c574f4d617511ebb2247729"],"state_sha256":"43d26f9798dc5f97a40044e22d00bb3f79313586d6888d960af3e88dc68f8e50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"alb6/dVv+jgsIMRXltIQ/J88jMqISVLRNuAlGrhRXGWwre9N/m/J4bYRn8bmz3Jo7FZe7yOPdUC9EVBYZXKyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:38:27.649141Z","bundle_sha256":"fc339e640720ee5dd3ffea86a985839e4cb20a197939dfb28c8b95da89309c1e"}}