{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SNBYEMAWWB6M4YSNZTTANCDBN6","short_pith_number":"pith:SNBYEMAW","canonical_record":{"source":{"id":"1706.06643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f01b6b90c58f66ebd509113fefebd4dd74ef820731c7d4d91d50ddb43130c1ff","abstract_canon_sha256":"4a3a941101eb33ddf7dde0703e2e89c79857fac8b6b3bd58f7247e2dfd85b3f5"},"schema_version":"1.0"},"canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","source":{"kind":"arxiv","id":"1706.06643","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06643","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06643v1","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06643","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"SNBYEMAWWB6M","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SNBYEMAWWB6M4YSN","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SNBYEMAW","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SNBYEMAWWB6M4YSNZTTANCDBN6","target":"record","payload":{"canonical_record":{"source":{"id":"1706.06643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f01b6b90c58f66ebd509113fefebd4dd74ef820731c7d4d91d50ddb43130c1ff","abstract_canon_sha256":"4a3a941101eb33ddf7dde0703e2e89c79857fac8b6b3bd58f7247e2dfd85b3f5"},"schema_version":"1.0"},"canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:57.339545Z","signature_b64":"2Irqpa2UQgG1EGva8DmoOSGL5pnJf1PCTOZs3NCbYlZh92KTGI9exhOoD41vWLnLirBY/X/QP6iSH9hStFx+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","last_reissued_at":"2026-05-18T00:41:57.338751Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:57.338751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.06643","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":"2026-05-18T00:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UiQpN761SyUUQuvaYdq6bq6aN5VQ50fp8iP1sChLoavknxlNal1JDG9UQhc+08k1gKcC78SYBFxjhItDqlLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:12:36.977918Z"},"content_sha256":"3b96b7e6f86b5142cf01cab60c41313638e20035d70dbfc288d4dcbc0b33ea7a","schema_version":"1.0","event_id":"sha256:3b96b7e6f86b5142cf01cab60c41313638e20035d70dbfc288d4dcbc0b33ea7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SNBYEMAWWB6M4YSNZTTANCDBN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2017-06-20T19:47:44Z","abstract_excerpt":"We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06643","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":"2026-05-18T00:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OdO8DtNqcOCjkNX4AhrE+GvmYVd61+yRmY6JIydhJwGQGO1M/ID1W+RWCZx5ihZ41sfjRY9we2KZOWTA73NuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:12:36.978598Z"},"content_sha256":"c856d11652002c69ec692d36aa921f0e6afab84261cd18fb8b2732a5eeec6266","schema_version":"1.0","event_id":"sha256:c856d11652002c69ec692d36aa921f0e6afab84261cd18fb8b2732a5eeec6266"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/bundle.json","state_url":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/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":"2026-06-06T17:12:36Z","links":{"resolver":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6","bundle":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/bundle.json","state":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SNBYEMAWWB6M4YSNZTTANCDBN6","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":"4a3a941101eb33ddf7dde0703e2e89c79857fac8b6b3bd58f7247e2dfd85b3f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","title_canon_sha256":"f01b6b90c58f66ebd509113fefebd4dd74ef820731c7d4d91d50ddb43130c1ff"},"schema_version":"1.0","source":{"id":"1706.06643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06643","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06643v1","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06643","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"SNBYEMAWWB6M","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SNBYEMAWWB6M4YSN","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SNBYEMAW","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:c856d11652002c69ec692d36aa921f0e6afab84261cd18fb8b2732a5eeec6266","target":"graph","created_at":"2026-05-18T00:41:57Z","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":"We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000).","authors_text":"Emma Brunskill, Philip S. Thomas","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06643","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":"sha256:3b96b7e6f86b5142cf01cab60c41313638e20035d70dbfc288d4dcbc0b33ea7a","target":"record","created_at":"2026-05-18T00:41:57Z","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":"4a3a941101eb33ddf7dde0703e2e89c79857fac8b6b3bd58f7247e2dfd85b3f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","title_canon_sha256":"f01b6b90c58f66ebd509113fefebd4dd74ef820731c7d4d91d50ddb43130c1ff"},"schema_version":"1.0","source":{"id":"1706.06643","kind":"arxiv","version":1}},"canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","first_computed_at":"2026-05-18T00:41:57.338751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:57.338751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Irqpa2UQgG1EGva8DmoOSGL5pnJf1PCTOZs3NCbYlZh92KTGI9exhOoD41vWLnLirBY/X/QP6iSH9hStFx+BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:57.339545Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.06643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b96b7e6f86b5142cf01cab60c41313638e20035d70dbfc288d4dcbc0b33ea7a","sha256:c856d11652002c69ec692d36aa921f0e6afab84261cd18fb8b2732a5eeec6266"],"state_sha256":"fb3c65a30fe7fa9eaeb70ec479966fcf12d181db66cd4d5ca16eb254fcd07747"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2O7IKACbVHNiN5UtU3lar0+DcxC22SEcqcY6hFpz81OcW3HPqq06V73dxvWiW+SN0sCRgC3tE6HwrpKSWk+jBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T17:12:36.982270Z","bundle_sha256":"6fbf1ae49920a6d4b3bb86abc2e1734a93b185259afdb2019bd7d0aefb47af65"}}