{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GNQ4T4VYUTSTDXNHW26R6ZIFCM","short_pith_number":"pith:GNQ4T4VY","canonical_record":{"source":{"id":"1709.04073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"c90027f8838fe410c5a074a93b1947cbe1d7748cd0bee2998fb8f566ba36a59b","abstract_canon_sha256":"b6022751bf89a0770d358889d8c05c24502889c3c3052e4e30bd84aaeb1c6686"},"schema_version":"1.0"},"canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","source":{"kind":"arxiv","id":"1709.04073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04073","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04073v1","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04073","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"GNQ4T4VYUTST","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GNQ4T4VYUTSTDXNH","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GNQ4T4VY","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GNQ4T4VYUTSTDXNHW26R6ZIFCM","target":"record","payload":{"canonical_record":{"source":{"id":"1709.04073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"c90027f8838fe410c5a074a93b1947cbe1d7748cd0bee2998fb8f566ba36a59b","abstract_canon_sha256":"b6022751bf89a0770d358889d8c05c24502889c3c3052e4e30bd84aaeb1c6686"},"schema_version":"1.0"},"canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:15.527195Z","signature_b64":"Omo9TvYJblQsT23UBOYhnSuFdHPMQVZio79E3E1+w8ei5RoMIKmMJM01epa8eIs933f50b3JJyczxRih+JFZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","last_reissued_at":"2026-05-18T00:35:15.526514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:15.526514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.04073","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":"2026-05-18T00:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tybx0dgXwO8AE8JYj4nlalAnn8Q/eV51yFegCN7cK0XZKiDclaINFh/qqUUDZow1jmraOTNNRwfROb8TY8raDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:30:11.045694Z"},"content_sha256":"8cfdfff59889b6d209764ad7615ced8e0afbf5ac2ee18b42a7381eb2b0964aa7","schema_version":"1.0","event_id":"sha256:8cfdfff59889b6d209764ad7615ced8e0afbf5ac2ee18b42a7381eb2b0964aa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GNQ4T4VYUTSTDXNHW26R6ZIFCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandrashekar Lakshminarayanan, Csaba Szepesv\\'ari","submitted_at":"2017-09-12T22:34:09Z","abstract_excerpt":"We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate $\\theta_{*} \\in \\mathbb{R}^d$ (that is an optimum or a fixed point) using noisy data and $O(d)$ updates per iteration. In this paper, we are motivated by the problem (in RL) of policy evaluation from experience replay using the \\emph{temporal difference} (TD) class of learning algorithms that are also LSAs. For LS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04073","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":"2026-05-18T00:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMX/fKB3AmmDf7hTsB+c5kji0ns/ehUip1NVDQyUFHTiU9TgNJkojayMRrzcHKvikTc2nOXOooQ9eKfaVwtuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:30:11.046292Z"},"content_sha256":"0412662a1e270049fd0e000beb4cfae6a5825fd3a2b182781b005f1adc20bc39","schema_version":"1.0","event_id":"sha256:0412662a1e270049fd0e000beb4cfae6a5825fd3a2b182781b005f1adc20bc39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/bundle.json","state_url":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/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":"2026-05-28T03:30:11Z","links":{"resolver":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM","bundle":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/bundle.json","state":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GNQ4T4VYUTSTDXNHW26R6ZIFCM","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":"b6022751bf89a0770d358889d8c05c24502889c3c3052e4e30bd84aaeb1c6686","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","title_canon_sha256":"c90027f8838fe410c5a074a93b1947cbe1d7748cd0bee2998fb8f566ba36a59b"},"schema_version":"1.0","source":{"id":"1709.04073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04073","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04073v1","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04073","created_at":"2026-05-18T00:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"GNQ4T4VYUTST","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GNQ4T4VYUTSTDXNH","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GNQ4T4VY","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:0412662a1e270049fd0e000beb4cfae6a5825fd3a2b182781b005f1adc20bc39","target":"graph","created_at":"2026-05-18T00:35:15Z","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":"We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate $\\theta_{*} \\in \\mathbb{R}^d$ (that is an optimum or a fixed point) using noisy data and $O(d)$ updates per iteration. In this paper, we are motivated by the problem (in RL) of policy evaluation from experience replay using the \\emph{temporal difference} (TD) class of learning algorithms that are also LSAs. For LS","authors_text":"Chandrashekar Lakshminarayanan, Csaba Szepesv\\'ari","cross_cats":["cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","title":"Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04073","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":"sha256:8cfdfff59889b6d209764ad7615ced8e0afbf5ac2ee18b42a7381eb2b0964aa7","target":"record","created_at":"2026-05-18T00:35:15Z","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":"b6022751bf89a0770d358889d8c05c24502889c3c3052e4e30bd84aaeb1c6686","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","title_canon_sha256":"c90027f8838fe410c5a074a93b1947cbe1d7748cd0bee2998fb8f566ba36a59b"},"schema_version":"1.0","source":{"id":"1709.04073","kind":"arxiv","version":1}},"canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","first_computed_at":"2026-05-18T00:35:15.526514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:15.526514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Omo9TvYJblQsT23UBOYhnSuFdHPMQVZio79E3E1+w8ei5RoMIKmMJM01epa8eIs933f50b3JJyczxRih+JFZBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:15.527195Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.04073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cfdfff59889b6d209764ad7615ced8e0afbf5ac2ee18b42a7381eb2b0964aa7","sha256:0412662a1e270049fd0e000beb4cfae6a5825fd3a2b182781b005f1adc20bc39"],"state_sha256":"a3636fb9060d72f67c4c0b4442d765eba3e75d2289cfb81ec6119566d81b1f6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DmmLiiePVlUgNl4TMlw0DaHUPbqb42XsabWS+9le5vy88OeqHOu8lLfK8+qnzdKNUsGjV/DsAZFMHpoPLbQkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T03:30:11.049404Z","bundle_sha256":"d65790d4e11922b56fdebefbad047c8d3776ae9fd860161fd378f40db24bc3f6"}}