{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:ISGEO6BEZV3SAX7DCGGQJ4BEVU","short_pith_number":"pith:ISGEO6BE","canonical_record":{"source":{"id":"1412.6734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"595559e2c5dd53bd468eed1a7ccf7e07beb2809c1b40e36dac19fbf794fdf6b0","abstract_canon_sha256":"bd544cd29f43100ed227f421ecc3816b7fcde0ec91b6297b2b43224664e2bbfe"},"schema_version":"1.0"},"canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","source":{"kind":"arxiv","id":"1412.6734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6734","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6734v1","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6734","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"pith_short_12","alias_value":"ISGEO6BEZV3S","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"ISGEO6BEZV3SAX7D","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"ISGEO6BE","created_at":"2026-05-18T12:28:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:ISGEO6BEZV3SAX7DCGGQJ4BEVU","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"595559e2c5dd53bd468eed1a7ccf7e07beb2809c1b40e36dac19fbf794fdf6b0","abstract_canon_sha256":"bd544cd29f43100ed227f421ecc3816b7fcde0ec91b6297b2b43224664e2bbfe"},"schema_version":"1.0"},"canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:46.338052Z","signature_b64":"EJ9tq0Ap+T+9Kslu/qNyivdDAZ0Tw2jfG+SBUPc62oFJUak0SP3yy4N6o9Dr3501h26lzsmVGZ+gO3C8iW8zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","last_reissued_at":"2026-05-18T02:30:46.337654Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:46.337654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6734","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":"2026-05-18T02:30:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zhid9O5wQ3kb/LkXqaNP5jp+//e9/5za5gMPGIst/QZXqLNRBvkl7iGoM8SgLdvjP8EdyUA3aklnRlJmYYh3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:13.792810Z"},"content_sha256":"ff4bf23410633aa787e40a6c81a25e03140985a02203e9ab57bb31e560f5de4e","schema_version":"1.0","event_id":"sha256:ff4bf23410633aa787e40a6c81a25e03140985a02203e9ab57bb31e560f5de4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:ISGEO6BEZV3SAX7DCGGQJ4BEVU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aviv Tamar, Edoardo M. Airoldi, Panos Toulis, Shie Mannor","submitted_at":"2014-12-21T06:53:15Z","abstract_excerpt":"In reinforcement learning, the TD($\\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\\lambda$) is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size leads to fast convergence, at the cost of higher variance and risk of instability. In this work, we introduce the implicit TD($\\lambda$) algorithm which has the same function and computational cost as TD($\\lambda$), but is significantly more stable. We provide a theore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6734","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":"2026-05-18T02:30:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hB+Wb5ZxyyrZ4D7BGmlR7W3aWilW7B4T2jPU9U6c8umE3Lh4hXeifzIzYPydQVZ3AYCDrTx17YHVumYUehbcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:13.793522Z"},"content_sha256":"90e955ebd0ed582344e635b2906ac46b6603ede8881dc79d1ef8863b48a4a485","schema_version":"1.0","event_id":"sha256:90e955ebd0ed582344e635b2906ac46b6603ede8881dc79d1ef8863b48a4a485"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/bundle.json","state_url":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/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":"2026-05-25T22:04:13Z","links":{"resolver":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU","bundle":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/bundle.json","state":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:ISGEO6BEZV3SAX7DCGGQJ4BEVU","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":"bd544cd29f43100ed227f421ecc3816b7fcde0ec91b6297b2b43224664e2bbfe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","title_canon_sha256":"595559e2c5dd53bd468eed1a7ccf7e07beb2809c1b40e36dac19fbf794fdf6b0"},"schema_version":"1.0","source":{"id":"1412.6734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6734","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6734v1","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6734","created_at":"2026-05-18T02:30:46Z"},{"alias_kind":"pith_short_12","alias_value":"ISGEO6BEZV3S","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"ISGEO6BEZV3SAX7D","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"ISGEO6BE","created_at":"2026-05-18T12:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:90e955ebd0ed582344e635b2906ac46b6603ede8881dc79d1ef8863b48a4a485","target":"graph","created_at":"2026-05-18T02:30:46Z","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":"In reinforcement learning, the TD($\\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\\lambda$) is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size leads to fast convergence, at the cost of higher variance and risk of instability. In this work, we introduce the implicit TD($\\lambda$) algorithm which has the same function and computational cost as TD($\\lambda$), but is significantly more stable. We provide a theore","authors_text":"Aviv Tamar, Edoardo M. Airoldi, Panos Toulis, Shie Mannor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","title":"Implicit Temporal Differences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6734","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:ff4bf23410633aa787e40a6c81a25e03140985a02203e9ab57bb31e560f5de4e","target":"record","created_at":"2026-05-18T02:30:46Z","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":"bd544cd29f43100ed227f421ecc3816b7fcde0ec91b6297b2b43224664e2bbfe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","title_canon_sha256":"595559e2c5dd53bd468eed1a7ccf7e07beb2809c1b40e36dac19fbf794fdf6b0"},"schema_version":"1.0","source":{"id":"1412.6734","kind":"arxiv","version":1}},"canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","first_computed_at":"2026-05-18T02:30:46.337654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:30:46.337654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJ9tq0Ap+T+9Kslu/qNyivdDAZ0Tw2jfG+SBUPc62oFJUak0SP3yy4N6o9Dr3501h26lzsmVGZ+gO3C8iW8zCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:30:46.338052Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff4bf23410633aa787e40a6c81a25e03140985a02203e9ab57bb31e560f5de4e","sha256:90e955ebd0ed582344e635b2906ac46b6603ede8881dc79d1ef8863b48a4a485"],"state_sha256":"36b27a0228f9ad03713674f3e839759fd88fda2a9e85d6341d8e67b8dae44e3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MugV/OlPV2Z48k/wb3zTH5n8EUyrxe/fZ9sk0lh4q95lbeXIPNK7vz8IfBG5Ca1ULmRXgITludVsAzSUsAwjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:04:13.797145Z","bundle_sha256":"130783a4c461ec6b82dfc105d8810abc9729e9f48dc9993809f2ba733a3ed0cd"}}