{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PVRPDEH2JCVGZPM7QBWKMIQIGY","short_pith_number":"pith:PVRPDEH2","canonical_record":{"source":{"id":"1808.09127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-08-28T05:39:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae790e972b9c57a902583ad2d9006a44bef2a6bc7ec768b5a082613e665f509c","abstract_canon_sha256":"71af2abed8caa05e1221891a9388fad6090b7cdc3427bab35fa3d890fa44f999"},"schema_version":"1.0"},"canonical_sha256":"7d62f190fa48aa6cbd9f806ca622083618b452823dd069ce077a1ca51e6ca0ab","source":{"kind":"arxiv","id":"1808.09127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09127","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09127v1","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09127","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"PVRPDEH2JCVG","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PVRPDEH2JCVGZPM7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PVRPDEH2","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PVRPDEH2JCVGZPM7QBWKMIQIGY","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-08-28T05:39:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae790e972b9c57a902583ad2d9006a44bef2a6bc7ec768b5a082613e665f509c","abstract_canon_sha256":"71af2abed8caa05e1221891a9388fad6090b7cdc3427bab35fa3d890fa44f999"},"schema_version":"1.0"},"canonical_sha256":"7d62f190fa48aa6cbd9f806ca622083618b452823dd069ce077a1ca51e6ca0ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:04.413676Z","signature_b64":"yf2HmGdQ0SI3jOZkzinveMfvWal/RyFkVNqCFsFcd740Ya7ynlHzg7h9/Jv4eU4yeWX+SKU3vICOzth49RbyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d62f190fa48aa6cbd9f806ca622083618b452823dd069ce077a1ca51e6ca0ab","last_reissued_at":"2026-05-18T00:07:04.412912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:04.412912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09127","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":"2026-05-18T00:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"stn0rfn0oSNbJt8i/lQs3Sdkw/tsSiv4s9Qshd+xv/VmYtSZBYX0lMiBUhPaOwGYyC00a41xqEfLDc6PgS+uCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T21:38:22.177346Z"},"content_sha256":"28a5acd9973bfa9b16cbc0c2cbadee91e3ee7dc1fae06ded4c56cbf55f26df8e","schema_version":"1.0","event_id":"sha256:28a5acd9973bfa9b16cbc0c2cbadee91e3ee7dc1fae06ded4c56cbf55f26df8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PVRPDEH2JCVGZPM7QBWKMIQIGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-confidence error estimates for learned value functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Martha White, Touqir Sajed, Wesley Chung","submitted_at":"2018-08-28T05:39:48Z","abstract_excerpt":"Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the properties of these algorithms, the experimenter needs high-confidence estimates of the accuracy of the learned value functions. For environments with small, finite state-spaces, like chains, the true value function can be easily computed, to compute accuracy. For large, or continuou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09127","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":"2026-05-18T00:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l78AFvtj3zHhEPyo4ooTQNc3oP5Fxt4FwWsuOsRHW5Ci/iDxaeMc/+QNzlinZVl9wHcu1LgHUvx9LXpSQwGxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T21:38:22.177739Z"},"content_sha256":"9947a52446cc5504de50a2726977152a44fcc168f491064552efa857dcc345d3","schema_version":"1.0","event_id":"sha256:9947a52446cc5504de50a2726977152a44fcc168f491064552efa857dcc345d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/bundle.json","state_url":"https://pith.science/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/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":"2026-05-20T21:38:22Z","links":{"resolver":"https://pith.science/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY","bundle":"https://pith.science/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/bundle.json","state":"https://pith.science/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVRPDEH2JCVGZPM7QBWKMIQIGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PVRPDEH2JCVGZPM7QBWKMIQIGY","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":"71af2abed8caa05e1221891a9388fad6090b7cdc3427bab35fa3d890fa44f999","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-08-28T05:39:48Z","title_canon_sha256":"ae790e972b9c57a902583ad2d9006a44bef2a6bc7ec768b5a082613e665f509c"},"schema_version":"1.0","source":{"id":"1808.09127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09127","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09127v1","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09127","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"PVRPDEH2JCVG","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PVRPDEH2JCVGZPM7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PVRPDEH2","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:9947a52446cc5504de50a2726977152a44fcc168f491064552efa857dcc345d3","target":"graph","created_at":"2026-05-18T00:07:04Z","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":"Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the properties of these algorithms, the experimenter needs high-confidence estimates of the accuracy of the learned value functions. For environments with small, finite state-spaces, like chains, the true value function can be easily computed, to compute accuracy. For large, or continuou","authors_text":"Martha White, Touqir Sajed, Wesley Chung","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-08-28T05:39:48Z","title":"High-confidence error estimates for learned value functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09127","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":"sha256:28a5acd9973bfa9b16cbc0c2cbadee91e3ee7dc1fae06ded4c56cbf55f26df8e","target":"record","created_at":"2026-05-18T00:07:04Z","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":"71af2abed8caa05e1221891a9388fad6090b7cdc3427bab35fa3d890fa44f999","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-08-28T05:39:48Z","title_canon_sha256":"ae790e972b9c57a902583ad2d9006a44bef2a6bc7ec768b5a082613e665f509c"},"schema_version":"1.0","source":{"id":"1808.09127","kind":"arxiv","version":1}},"canonical_sha256":"7d62f190fa48aa6cbd9f806ca622083618b452823dd069ce077a1ca51e6ca0ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d62f190fa48aa6cbd9f806ca622083618b452823dd069ce077a1ca51e6ca0ab","first_computed_at":"2026-05-18T00:07:04.412912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:04.412912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yf2HmGdQ0SI3jOZkzinveMfvWal/RyFkVNqCFsFcd740Ya7ynlHzg7h9/Jv4eU4yeWX+SKU3vICOzth49RbyCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:04.413676Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28a5acd9973bfa9b16cbc0c2cbadee91e3ee7dc1fae06ded4c56cbf55f26df8e","sha256:9947a52446cc5504de50a2726977152a44fcc168f491064552efa857dcc345d3"],"state_sha256":"87a884afd7767bc2d38f99d7d2919ad2fe4c1eef815e9b912ef50cf1b8ba43a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ct6TRkFnmBtMcVzd/oxtPjwsqu8mcYLEnEsG3aVE4UVADRn9FhtfFEJRJOK9P9G5JVL6/X9UFkKG2JI+fneTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T21:38:22.180123Z","bundle_sha256":"23d24281deaab8aa207695abe323b4efc296ebf2d8f533ec11dfeed190427721"}}