{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:Z3YVKLCGMYULFJMGAKQVO24JNC","short_pith_number":"pith:Z3YVKLCG","canonical_record":{"source":{"id":"1602.08771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-28T21:23:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"390e8b5c17f2bd51c4628d00ffa80466b920b75dec07a7b81e3382f2fc0a69f4","abstract_canon_sha256":"f7191ce0d76d9482282540b63e951ed2434bb9b27a3b590da275a26b85a2f592"},"schema_version":"1.0"},"canonical_sha256":"cef1552c466628b2a58602a1576b8968958cb470e12c2afe34c042b9633d2fe2","source":{"kind":"arxiv","id":"1602.08771","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.08771","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.08771v2","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.08771","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z3YVKLCGMYUL","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z3YVKLCGMYULFJMG","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z3YVKLCG","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:Z3YVKLCGMYULFJMGAKQVO24JNC","target":"record","payload":{"canonical_record":{"source":{"id":"1602.08771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-28T21:23:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"390e8b5c17f2bd51c4628d00ffa80466b920b75dec07a7b81e3382f2fc0a69f4","abstract_canon_sha256":"f7191ce0d76d9482282540b63e951ed2434bb9b27a3b590da275a26b85a2f592"},"schema_version":"1.0"},"canonical_sha256":"cef1552c466628b2a58602a1576b8968958cb470e12c2afe34c042b9633d2fe2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:59.181828Z","signature_b64":"uC5lpuqh6gy3LcUNW4HO8ld3CTPXAljro5iFbK8fa27zjEuMXXYMfbWk9i/OMPQN+XL0NYgigZSg6FbBdumjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef1552c466628b2a58602a1576b8968958cb470e12c2afe34c042b9633d2fe2","last_reissued_at":"2026-05-18T01:17:59.180972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:59.180972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.08771","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUm3t4sC0pEa6MfULbApmY6z1VQQx/kqn61TcDgYwsNUsk8WEzd2s1gDEk+QZ9Mj2+bA7a54iElozMeW9pMDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:56:50.486268Z"},"content_sha256":"d3d8f79f66ad024cfea5d25458285827661cb39dccac77a23b5c1068e8fd80b0","schema_version":"1.0","event_id":"sha256:d3d8f79f66ad024cfea5d25458285827661cb39dccac77a23b5c1068e8fd80b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:Z3YVKLCGMYULFJMGAKQVO24JNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating practical linear temporal difference learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam White, Martha White","submitted_at":"2016-02-28T21:23:54Z","abstract_excerpt":"Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcement learning: combining robustness to off-policy sampling, function approximation, linear complexity, and temporal difference (TD) updates. This paper contains two main contributions. First, we derive two new hybrid TD policy-evaluation algorithms, which fill a gap in this collec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.08771","kind":"arxiv","version":2},"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":"2026-05-18T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCL2fPWztmqDAaTevA7cT4YWIeGvT8aMr6ak/2sBLMuF39YSlVq+oKHEC5MGhwuebPSG9KdamM5L7LrTSMtEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:56:50.486641Z"},"content_sha256":"51e6c3b8cfa2c76748da9a763a16d4fd73b6d03c1dae302d8ec71c31cd55345e","schema_version":"1.0","event_id":"sha256:51e6c3b8cfa2c76748da9a763a16d4fd73b6d03c1dae302d8ec71c31cd55345e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/bundle.json","state_url":"https://pith.science/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/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":"2026-06-01T04:56:50Z","links":{"resolver":"https://pith.science/pith/Z3YVKLCGMYULFJMGAKQVO24JNC","bundle":"https://pith.science/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/bundle.json","state":"https://pith.science/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3YVKLCGMYULFJMGAKQVO24JNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Z3YVKLCGMYULFJMGAKQVO24JNC","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":"f7191ce0d76d9482282540b63e951ed2434bb9b27a3b590da275a26b85a2f592","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-28T21:23:54Z","title_canon_sha256":"390e8b5c17f2bd51c4628d00ffa80466b920b75dec07a7b81e3382f2fc0a69f4"},"schema_version":"1.0","source":{"id":"1602.08771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.08771","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.08771v2","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.08771","created_at":"2026-05-18T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z3YVKLCGMYUL","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z3YVKLCGMYULFJMG","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z3YVKLCG","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:51e6c3b8cfa2c76748da9a763a16d4fd73b6d03c1dae302d8ec71c31cd55345e","target":"graph","created_at":"2026-05-18T01:17:59Z","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":"Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcement learning: combining robustness to off-policy sampling, function approximation, linear complexity, and temporal difference (TD) updates. This paper contains two main contributions. First, we derive two new hybrid TD policy-evaluation algorithms, which fill a gap in this collec","authors_text":"Adam White, Martha White","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-28T21:23:54Z","title":"Investigating practical linear temporal difference learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.08771","kind":"arxiv","version":2},"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:d3d8f79f66ad024cfea5d25458285827661cb39dccac77a23b5c1068e8fd80b0","target":"record","created_at":"2026-05-18T01:17:59Z","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":"f7191ce0d76d9482282540b63e951ed2434bb9b27a3b590da275a26b85a2f592","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-28T21:23:54Z","title_canon_sha256":"390e8b5c17f2bd51c4628d00ffa80466b920b75dec07a7b81e3382f2fc0a69f4"},"schema_version":"1.0","source":{"id":"1602.08771","kind":"arxiv","version":2}},"canonical_sha256":"cef1552c466628b2a58602a1576b8968958cb470e12c2afe34c042b9633d2fe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cef1552c466628b2a58602a1576b8968958cb470e12c2afe34c042b9633d2fe2","first_computed_at":"2026-05-18T01:17:59.180972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:59.180972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uC5lpuqh6gy3LcUNW4HO8ld3CTPXAljro5iFbK8fa27zjEuMXXYMfbWk9i/OMPQN+XL0NYgigZSg6FbBdumjAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:59.181828Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.08771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3d8f79f66ad024cfea5d25458285827661cb39dccac77a23b5c1068e8fd80b0","sha256:51e6c3b8cfa2c76748da9a763a16d4fd73b6d03c1dae302d8ec71c31cd55345e"],"state_sha256":"9be3ec9ff8652843c422fa6f22023dc6eea63283cd7d302b02ea460634541221"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BN20tM3TXQzVIXAexrm55i6toYCu0iB/Pq8JUaT+JNm6wEW/mVomZXqVZzX979+BzHmWp0VZrp5Ii4PMwVCUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:56:50.488548Z","bundle_sha256":"b9448839a17b216d26ddafc31224141e14f5d057424add74000ac724a0b96fcd"}}