{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RKVXXUIUAJ54CT5KDSPWUKQEAL","short_pith_number":"pith:RKVXXUIU","canonical_record":{"source":{"id":"1508.03411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-14T03:34:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3344a1b5c1804f9ed028ab9f7dbc27a15e6025b7f8e503110c40eb824ef8c811","abstract_canon_sha256":"4cf436ef5259b67ca2b6a8f23ea7df9f771e23ad3ef4f5e3d87f26ebefbcf3cd"},"schema_version":"1.0"},"canonical_sha256":"8aab7bd114027bc14faa1c9f6a2a0402e1b49ffb713464c0da0ce39705edeeb7","source":{"kind":"arxiv","id":"1508.03411","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03411","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03411v2","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03411","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"RKVXXUIUAJ54","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RKVXXUIUAJ54CT5K","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RKVXXUIU","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RKVXXUIUAJ54CT5KDSPWUKQEAL","target":"record","payload":{"canonical_record":{"source":{"id":"1508.03411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-14T03:34:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3344a1b5c1804f9ed028ab9f7dbc27a15e6025b7f8e503110c40eb824ef8c811","abstract_canon_sha256":"4cf436ef5259b67ca2b6a8f23ea7df9f771e23ad3ef4f5e3d87f26ebefbcf3cd"},"schema_version":"1.0"},"canonical_sha256":"8aab7bd114027bc14faa1c9f6a2a0402e1b49ffb713464c0da0ce39705edeeb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:54.200188Z","signature_b64":"l+rS92osTezhEh1eW6Gmb2efYaYTaApOX6mpUWwsJb5DsqI/o9VzEyvdeCcEFOP/62n/18xX9N9PGglEpmQfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aab7bd114027bc14faa1c9f6a2a0402e1b49ffb713464c0da0ce39705edeeb7","last_reissued_at":"2026-05-18T01:34:54.199640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:54.199640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.03411","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":"2026-05-18T01:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLCumOD1SjDizgSLkPIYXvWhX0FyioH2eTSaHY2Kw90sru+/OR3r4peDIqd0CZPRlCyiH0PuIqdnCWm1S72eAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:32:44.133298Z"},"content_sha256":"3a476a2cc93df8a0e564630e15f1f5b9d0e2d773f528552f1728052fe9994031","schema_version":"1.0","event_id":"sha256:3a476a2cc93df8a0e564630e15f1f5b9d0e2d773f528552f1728052fe9994031"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RKVXXUIUAJ54CT5KDSPWUKQEAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emphatic TD Bellman Operator is a Contraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Assaf Hallak, Aviv Tamar, Shie Mannor","submitted_at":"2015-08-14T03:34:10Z","abstract_excerpt":"Recently, \\citet{SuttonMW15} introduced the emphatic temporal differences (ETD) algorithm for off-policy evaluation in Markov decision processes. In this short note, we show that the projected fixed-point equation that underlies ETD involves a contraction operator, with a $\\sqrt{\\gamma}$-contraction modulus (where $\\gamma$ is the discount factor). This allows us to provide error bounds on the approximation error of ETD. To our knowledge, these are the first error bounds for an off-policy evaluation algorithm under general target and behavior policies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03411","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":"2026-05-18T01:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HqxAgfKi7Vo/2Ldc5Zlf/AraFNVtdEQ5PPiyZlAErfywquAbzQd077qxj3MkspME5MmJhoz9iUOk9ZSM9smfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:32:44.134055Z"},"content_sha256":"ee27dff1e4b53ff56fb801a42f28b335bf9faee2af6be4b2f8463a01e143f012","schema_version":"1.0","event_id":"sha256:ee27dff1e4b53ff56fb801a42f28b335bf9faee2af6be4b2f8463a01e143f012"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/bundle.json","state_url":"https://pith.science/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/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":"2026-05-31T02:32:44Z","links":{"resolver":"https://pith.science/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL","bundle":"https://pith.science/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/bundle.json","state":"https://pith.science/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKVXXUIUAJ54CT5KDSPWUKQEAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RKVXXUIUAJ54CT5KDSPWUKQEAL","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":"4cf436ef5259b67ca2b6a8f23ea7df9f771e23ad3ef4f5e3d87f26ebefbcf3cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-14T03:34:10Z","title_canon_sha256":"3344a1b5c1804f9ed028ab9f7dbc27a15e6025b7f8e503110c40eb824ef8c811"},"schema_version":"1.0","source":{"id":"1508.03411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03411","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03411v2","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03411","created_at":"2026-05-18T01:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"RKVXXUIUAJ54","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RKVXXUIUAJ54CT5K","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RKVXXUIU","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:ee27dff1e4b53ff56fb801a42f28b335bf9faee2af6be4b2f8463a01e143f012","target":"graph","created_at":"2026-05-18T01:34:54Z","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":"Recently, \\citet{SuttonMW15} introduced the emphatic temporal differences (ETD) algorithm for off-policy evaluation in Markov decision processes. In this short note, we show that the projected fixed-point equation that underlies ETD involves a contraction operator, with a $\\sqrt{\\gamma}$-contraction modulus (where $\\gamma$ is the discount factor). This allows us to provide error bounds on the approximation error of ETD. To our knowledge, these are the first error bounds for an off-policy evaluation algorithm under general target and behavior policies.","authors_text":"Assaf Hallak, Aviv Tamar, Shie Mannor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-14T03:34:10Z","title":"Emphatic TD Bellman Operator is a Contraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03411","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":"sha256:3a476a2cc93df8a0e564630e15f1f5b9d0e2d773f528552f1728052fe9994031","target":"record","created_at":"2026-05-18T01:34:54Z","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":"4cf436ef5259b67ca2b6a8f23ea7df9f771e23ad3ef4f5e3d87f26ebefbcf3cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-14T03:34:10Z","title_canon_sha256":"3344a1b5c1804f9ed028ab9f7dbc27a15e6025b7f8e503110c40eb824ef8c811"},"schema_version":"1.0","source":{"id":"1508.03411","kind":"arxiv","version":2}},"canonical_sha256":"8aab7bd114027bc14faa1c9f6a2a0402e1b49ffb713464c0da0ce39705edeeb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aab7bd114027bc14faa1c9f6a2a0402e1b49ffb713464c0da0ce39705edeeb7","first_computed_at":"2026-05-18T01:34:54.199640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:54.199640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l+rS92osTezhEh1eW6Gmb2efYaYTaApOX6mpUWwsJb5DsqI/o9VzEyvdeCcEFOP/62n/18xX9N9PGglEpmQfDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:54.200188Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.03411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a476a2cc93df8a0e564630e15f1f5b9d0e2d773f528552f1728052fe9994031","sha256:ee27dff1e4b53ff56fb801a42f28b335bf9faee2af6be4b2f8463a01e143f012"],"state_sha256":"ee270b604456282fca326a1733076e4681597cc9aa91a27152a24ba1a79de070"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mphp25OS7XTMYHexraJ0hvcdYP53hXpCOgsRr+rE2PnYGq1QD00hImIRbQ+ip9WI77dvRG57lLFeigZRT+OnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T02:32:44.136992Z","bundle_sha256":"83b2e0335de796f4adff3ba778a6bcbda2cee8c990d213730f408f599a2adeb3"}}