{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4HH4SYWMZVEHYKI5U56FF5YEUT","short_pith_number":"pith:4HH4SYWM","canonical_record":{"source":{"id":"1906.03063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T16:09:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"97d0c774d09598cc58cd612a4d2792efb3cf2389156f2882d8206573f8ef9659","abstract_canon_sha256":"61a202961f504584a670632977e365411bfffeb9aa31dede8b1ce4beb7a6ea79"},"schema_version":"1.0"},"canonical_sha256":"e1cfc962cccd487c291da77c52f704a4fe7fe3d910fc06b87f48ff1e591e3a7b","source":{"kind":"arxiv","id":"1906.03063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03063","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03063v1","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03063","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"4HH4SYWMZVEH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4HH4SYWMZVEHYKI5","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4HH4SYWM","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4HH4SYWMZVEHYKI5U56FF5YEUT","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T16:09:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"97d0c774d09598cc58cd612a4d2792efb3cf2389156f2882d8206573f8ef9659","abstract_canon_sha256":"61a202961f504584a670632977e365411bfffeb9aa31dede8b1ce4beb7a6ea79"},"schema_version":"1.0"},"canonical_sha256":"e1cfc962cccd487c291da77c52f704a4fe7fe3d910fc06b87f48ff1e591e3a7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:55.191837Z","signature_b64":"pGKpjbm1Hm0O4ULsSjr/DwZyedb63QZeXM5BB309hAe+YidPN/vgxlllPNaRUk47cCRDiMA9dJq8plcg6T16Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1cfc962cccd487c291da77c52f704a4fe7fe3d910fc06b87f48ff1e591e3a7b","last_reissued_at":"2026-05-17T23:43:55.191125Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:55.191125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03063","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":"2026-05-17T23:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VmwXEROLmNQQVspeX9RsXaibrSOSXcKvOZWJ9kCC69sFabguBhZ76cLMyonnmpAKGUkr/bNd+38XwQgq5IdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T10:38:38.365295Z"},"content_sha256":"208dac1d44d5762d3a99233e0e67f8960264a4ee8e12290cc356004c8585c737","schema_version":"1.0","event_id":"sha256:208dac1d44d5762d3a99233e0e67f8960264a4ee8e12290cc356004c8585c737"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4HH4SYWMZVEHYKI5U56FF5YEUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Classical Policy Gradient: Preserving Bellman's Principle of Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris Nota, James Kostas, Philip S. Thomas, Scott M. Jordan, Yash Chandak","submitted_at":"2019-06-06T16:09:01Z","abstract_excerpt":"We propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman's principle of optimality, and provide an expression for the gradient of the objective."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03063","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":"2026-05-17T23:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FM1FmdS/yp8FHtLdD9FdU6He4dcKBLXMI4fWnaXcno25bB1rnzeDakcNP8ZjCpXRD/7DH6esuV3aHuuc2aL5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T10:38:38.365995Z"},"content_sha256":"f0600b7b4393c2c226d0a01ebe33f92895aa825f25617ea7535c540da4034730","schema_version":"1.0","event_id":"sha256:f0600b7b4393c2c226d0a01ebe33f92895aa825f25617ea7535c540da4034730"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/bundle.json","state_url":"https://pith.science/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/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":"2026-06-06T10:38:38Z","links":{"resolver":"https://pith.science/pith/4HH4SYWMZVEHYKI5U56FF5YEUT","bundle":"https://pith.science/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/bundle.json","state":"https://pith.science/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HH4SYWMZVEHYKI5U56FF5YEUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4HH4SYWMZVEHYKI5U56FF5YEUT","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":"61a202961f504584a670632977e365411bfffeb9aa31dede8b1ce4beb7a6ea79","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T16:09:01Z","title_canon_sha256":"97d0c774d09598cc58cd612a4d2792efb3cf2389156f2882d8206573f8ef9659"},"schema_version":"1.0","source":{"id":"1906.03063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03063","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03063v1","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03063","created_at":"2026-05-17T23:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"4HH4SYWMZVEH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4HH4SYWMZVEHYKI5","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4HH4SYWM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:f0600b7b4393c2c226d0a01ebe33f92895aa825f25617ea7535c540da4034730","target":"graph","created_at":"2026-05-17T23:43:55Z","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 propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman's principle of optimality, and provide an expression for the gradient of the objective.","authors_text":"Chris Nota, James Kostas, Philip S. Thomas, Scott M. Jordan, Yash Chandak","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T16:09:01Z","title":"Classical Policy Gradient: Preserving Bellman's Principle of Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03063","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":"sha256:208dac1d44d5762d3a99233e0e67f8960264a4ee8e12290cc356004c8585c737","target":"record","created_at":"2026-05-17T23:43:55Z","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":"61a202961f504584a670632977e365411bfffeb9aa31dede8b1ce4beb7a6ea79","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T16:09:01Z","title_canon_sha256":"97d0c774d09598cc58cd612a4d2792efb3cf2389156f2882d8206573f8ef9659"},"schema_version":"1.0","source":{"id":"1906.03063","kind":"arxiv","version":1}},"canonical_sha256":"e1cfc962cccd487c291da77c52f704a4fe7fe3d910fc06b87f48ff1e591e3a7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1cfc962cccd487c291da77c52f704a4fe7fe3d910fc06b87f48ff1e591e3a7b","first_computed_at":"2026-05-17T23:43:55.191125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:55.191125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pGKpjbm1Hm0O4ULsSjr/DwZyedb63QZeXM5BB309hAe+YidPN/vgxlllPNaRUk47cCRDiMA9dJq8plcg6T16Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:55.191837Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:208dac1d44d5762d3a99233e0e67f8960264a4ee8e12290cc356004c8585c737","sha256:f0600b7b4393c2c226d0a01ebe33f92895aa825f25617ea7535c540da4034730"],"state_sha256":"d218703850019300ad7517e956c20fc70bbd71ef99a37c32372c7ce1504d2ed2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcOcMyT9jYmGBPaBATwmhLLOR2fsO4CtWao04QWXjL4KItfZxGI1WwmbIYoFVn9o3eGdeKZZ2g5fT2j/4AAXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T10:38:38.369531Z","bundle_sha256":"f78971fd73f3361a3550ddd9dc921b7efbb0d2d76b65fc4f8e4c0f095bb46a9c"}}