{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2GX6FCHDLGSO53WFWA2N566IPG","short_pith_number":"pith:2GX6FCHD","canonical_record":{"source":{"id":"1711.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89de8ab25d438fe1e3c8bb087684018e239b9899a3f8bcc0697cd95a19a7f272","abstract_canon_sha256":"d61b3fa428ca6a5024d3687a7f89cd52382814ae5d77a2c7e847ba566dded354"},"schema_version":"1.0"},"canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","source":{"kind":"arxiv","id":"1711.08068","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08068","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08068v1","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08068","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"2GX6FCHDLGSO","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2GX6FCHDLGSO53WF","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2GX6FCHD","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2GX6FCHDLGSO53WFWA2N566IPG","target":"record","payload":{"canonical_record":{"source":{"id":"1711.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89de8ab25d438fe1e3c8bb087684018e239b9899a3f8bcc0697cd95a19a7f272","abstract_canon_sha256":"d61b3fa428ca6a5024d3687a7f89cd52382814ae5d77a2c7e847ba566dded354"},"schema_version":"1.0"},"canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:50.768418Z","signature_b64":"dSwldX927RcALNY5b+xF1eO2YyXn7KTTw3NZTOZzS1u4exDEkpgnea6dREleiWBEvBjQOGCl01DKcLH5MnW2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","last_reissued_at":"2026-05-18T00:29:50.767706Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:50.767706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.08068","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":"2026-05-18T00:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uh3PahJ28yuV+ghefM1s5HY55UtPNMM3j8LLH214FVnPD0q+4N8cKvz70D1RKoy/5sTF5yuLZQLkyMNYUg90DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T04:27:04.853345Z"},"content_sha256":"743fd3e62e6ab7f22a981d1df9edebe7529c02d6b069179514bd2337c12d1a29","schema_version":"1.0","event_id":"sha256:743fd3e62e6ab7f22a981d1df9edebe7529c02d6b069179514bd2337c12d1a29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2GX6FCHDLGSO53WFWA2N566IPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Levy, Stefano Ermon","submitted_at":"2017-11-21T22:05:18Z","abstract_excerpt":"Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08068","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":"2026-05-18T00:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Dh960sLy9tx+YreJeISciV9K7/Nq2kzI8F2HpY2KKyLAcu9x6nVTWciPQsl05hfOwVQvH1lb6tkedfpifXUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T04:27:04.853703Z"},"content_sha256":"38a6e2104c68c1924e48dadc51dc5fc75fd02f7dca744dd824f9540b0b0ea3ab","schema_version":"1.0","event_id":"sha256:38a6e2104c68c1924e48dadc51dc5fc75fd02f7dca744dd824f9540b0b0ea3ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/bundle.json","state_url":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GX6FCHDLGSO53WFWA2N566IPG/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":"2026-06-03T04:27:04Z","links":{"resolver":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG","bundle":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/bundle.json","state":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GX6FCHDLGSO53WFWA2N566IPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2GX6FCHDLGSO53WFWA2N566IPG","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":"d61b3fa428ca6a5024d3687a7f89cd52382814ae5d77a2c7e847ba566dded354","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","title_canon_sha256":"89de8ab25d438fe1e3c8bb087684018e239b9899a3f8bcc0697cd95a19a7f272"},"schema_version":"1.0","source":{"id":"1711.08068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08068","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08068v1","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08068","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"2GX6FCHDLGSO","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2GX6FCHDLGSO53WF","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2GX6FCHD","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:38a6e2104c68c1924e48dadc51dc5fc75fd02f7dca744dd824f9540b0b0ea3ab","target":"graph","created_at":"2026-05-18T00:29:50Z","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 optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new h","authors_text":"Daniel Levy, Stefano Ermon","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","title":"Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08068","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":"sha256:743fd3e62e6ab7f22a981d1df9edebe7529c02d6b069179514bd2337c12d1a29","target":"record","created_at":"2026-05-18T00:29:50Z","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":"d61b3fa428ca6a5024d3687a7f89cd52382814ae5d77a2c7e847ba566dded354","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","title_canon_sha256":"89de8ab25d438fe1e3c8bb087684018e239b9899a3f8bcc0697cd95a19a7f272"},"schema_version":"1.0","source":{"id":"1711.08068","kind":"arxiv","version":1}},"canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","first_computed_at":"2026-05-18T00:29:50.767706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:50.767706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dSwldX927RcALNY5b+xF1eO2YyXn7KTTw3NZTOZzS1u4exDEkpgnea6dREleiWBEvBjQOGCl01DKcLH5MnW2DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:50.768418Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:743fd3e62e6ab7f22a981d1df9edebe7529c02d6b069179514bd2337c12d1a29","sha256:38a6e2104c68c1924e48dadc51dc5fc75fd02f7dca744dd824f9540b0b0ea3ab"],"state_sha256":"8e6b65321c32a7a450f2b94725286e0ed756bd05895798df9c0f9ed0204685f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wvpfOOp1g1kw/VHuTMPZZGwZDU/lRi2monCc4ezl2Dm4JBoY5+Dt2xh1FJ4KQpfVm6G2J4kehtC3tCA3n/hAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T04:27:04.855608Z","bundle_sha256":"67397f548dc7a76a378686a909c7b02c4c3035165e2c71becb629b68064a1f21"}}