{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UWLLNXMOB4LMVZKAUFWHB24PMC","short_pith_number":"pith:UWLLNXMO","canonical_record":{"source":{"id":"2002.11833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T23:00:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"880623bc0cf2c253640d813277c1165d5c0da8cb7ec080bb37490886a0eb1dd4","abstract_canon_sha256":"04d0517af39f96b731e65f35e51bffe8314e475119d5ec1c4a788a568ee4017a"},"schema_version":"1.0"},"canonical_sha256":"a596b6dd8e0f16cae540a16c70eb8f60a66503d00215651da3fd406bdb16d5d3","source":{"kind":"arxiv","id":"2002.11833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11833","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11833v1","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11833","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_12","alias_value":"UWLLNXMOB4LM","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_16","alias_value":"UWLLNXMOB4LMVZKA","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_8","alias_value":"UWLLNXMO","created_at":"2026-07-05T00:44:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UWLLNXMOB4LMVZKAUFWHB24PMC","target":"record","payload":{"canonical_record":{"source":{"id":"2002.11833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T23:00:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"880623bc0cf2c253640d813277c1165d5c0da8cb7ec080bb37490886a0eb1dd4","abstract_canon_sha256":"04d0517af39f96b731e65f35e51bffe8314e475119d5ec1c4a788a568ee4017a"},"schema_version":"1.0"},"canonical_sha256":"a596b6dd8e0f16cae540a16c70eb8f60a66503d00215651da3fd406bdb16d5d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:09.508556Z","signature_b64":"9Y3Y7D4ghMIC/6guh4mvOl255Rj9a2naOsLPebnsAu4On6ZNsH68LllJzuiUfaasC743VzPoJjabLxCyJYJZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a596b6dd8e0f16cae540a16c70eb8f60a66503d00215651da3fd406bdb16d5d3","last_reissued_at":"2026-07-05T00:44:09.508056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:09.508056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.11833","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":"2026-07-05T00:44:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"51bWIz0cFcZXE9XmhsVyf1J8JABBscKcHc9Lx2jr8R0CWK0zHqahQbPE3sPhrJxibpXVuDsLlv6jSQMmjuAuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:28:09.138106Z"},"content_sha256":"9885cca95f29be0293a581f615c2983619fc3514b1bdb9a42ada1f3836f229ac","schema_version":"1.0","event_id":"sha256:9885cca95f29be0293a581f615c2983619fc3514b1bdb9a42ada1f3836f229ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UWLLNXMOB4LMVZKAUFWHB24PMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Evaluation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Jean Harb, Pierre-Luc Bacon, Tom Schaul","submitted_at":"2020-02-26T23:00:27Z","abstract_excerpt":"Many reinforcement learning algorithms use value functions to guide the search for better policies. These methods estimate the value of a single policy while generalizing across many states. The core idea of this paper is to flip this convention and estimate the value of many policies, for a single set of states. This approach opens up the possibility of performing direct gradient ascent in policy space without seeing any new data. The main challenge for this approach is finding a way to represent complex policies that facilitates learning and generalization. To address this problem, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11833","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.11833/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":"2026-07-05T00:44:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdjNearV1Ov69ED+ar0OIBlcTT0Y4QyvJMwKLHEywl0cw33YIU5L99dTtQliJoZ/DW/S9sgAKvbnek3H2tckCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:28:09.138488Z"},"content_sha256":"b387df7f869f024a9e7a2279d94ee0bdfb9efeb374913aa17a038a319ddc785d","schema_version":"1.0","event_id":"sha256:b387df7f869f024a9e7a2279d94ee0bdfb9efeb374913aa17a038a319ddc785d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/bundle.json","state_url":"https://pith.science/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/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":"2026-08-06T18:28:09Z","links":{"resolver":"https://pith.science/pith/UWLLNXMOB4LMVZKAUFWHB24PMC","bundle":"https://pith.science/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/bundle.json","state":"https://pith.science/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWLLNXMOB4LMVZKAUFWHB24PMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UWLLNXMOB4LMVZKAUFWHB24PMC","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":"04d0517af39f96b731e65f35e51bffe8314e475119d5ec1c4a788a568ee4017a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T23:00:27Z","title_canon_sha256":"880623bc0cf2c253640d813277c1165d5c0da8cb7ec080bb37490886a0eb1dd4"},"schema_version":"1.0","source":{"id":"2002.11833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11833","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11833v1","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11833","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_12","alias_value":"UWLLNXMOB4LM","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_16","alias_value":"UWLLNXMOB4LMVZKA","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_8","alias_value":"UWLLNXMO","created_at":"2026-07-05T00:44:09Z"}],"graph_snapshots":[{"event_id":"sha256:b387df7f869f024a9e7a2279d94ee0bdfb9efeb374913aa17a038a319ddc785d","target":"graph","created_at":"2026-07-05T00:44:09Z","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/2002.11833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many reinforcement learning algorithms use value functions to guide the search for better policies. These methods estimate the value of a single policy while generalizing across many states. The core idea of this paper is to flip this convention and estimate the value of many policies, for a single set of states. This approach opens up the possibility of performing direct gradient ascent in policy space without seeing any new data. The main challenge for this approach is finding a way to represent complex policies that facilitates learning and generalization. To address this problem, we introd","authors_text":"Doina Precup, Jean Harb, Pierre-Luc Bacon, Tom Schaul","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T23:00:27Z","title":"Policy Evaluation Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11833","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":"sha256:9885cca95f29be0293a581f615c2983619fc3514b1bdb9a42ada1f3836f229ac","target":"record","created_at":"2026-07-05T00:44:09Z","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":"04d0517af39f96b731e65f35e51bffe8314e475119d5ec1c4a788a568ee4017a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T23:00:27Z","title_canon_sha256":"880623bc0cf2c253640d813277c1165d5c0da8cb7ec080bb37490886a0eb1dd4"},"schema_version":"1.0","source":{"id":"2002.11833","kind":"arxiv","version":1}},"canonical_sha256":"a596b6dd8e0f16cae540a16c70eb8f60a66503d00215651da3fd406bdb16d5d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a596b6dd8e0f16cae540a16c70eb8f60a66503d00215651da3fd406bdb16d5d3","first_computed_at":"2026-07-05T00:44:09.508056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:09.508056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Y3Y7D4ghMIC/6guh4mvOl255Rj9a2naOsLPebnsAu4On6ZNsH68LllJzuiUfaasC743VzPoJjabLxCyJYJZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:09.508556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9885cca95f29be0293a581f615c2983619fc3514b1bdb9a42ada1f3836f229ac","sha256:b387df7f869f024a9e7a2279d94ee0bdfb9efeb374913aa17a038a319ddc785d"],"state_sha256":"0113f11a494c30fcf0dda59a5668090a4b85a519d9dcc8d6c459b419ffb3f452"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TsVEX+rBPx+Y9z6V+6b3p+S0U14aad6VksPhg1TxlTGIyFaC2XEXaMY2Hvf4ZdVovz/xGhQKbdSXO1xLdiTYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:28:09.141757Z","bundle_sha256":"50666f5cfd02be679e479ac88868290eb0698e015c78a489eae84cf57e84a696"}}