{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2","short_pith_number":"pith:QOA5QNG3","canonical_record":{"source":{"id":"1512.08562","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3","abstract_canon_sha256":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae"},"schema_version":"1.0"},"canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","source":{"kind":"arxiv","id":"1512.08562","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"1512.08562v4","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"QOA5QNG3U2R3","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QOA5QNG3U2R3MSNH","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QOA5QNG3","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2","target":"record","payload":{"canonical_record":{"source":{"id":"1512.08562","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3","abstract_canon_sha256":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae"},"schema_version":"1.0"},"canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:45.418918Z","signature_b64":"eYm6azdp8FCIs9ulC3TUhnAZ2mPc9nMRolyCYyBZe1cSocEEhaskwD67Bg8bJcveJl9VfWXHRIcfEhMPYGx9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","last_reissued_at":"2026-05-18T00:24:45.418249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:45.418249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.08562","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvNYxp6s7A453oBtphzEB7w6NdDzD+7Jwg5fy3lg3BW3etokvZGsdBlfKk95+kns4noFmLtpEH+uUdoizTzSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:19:27.340545Z"},"content_sha256":"11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5","schema_version":"1.0","event_id":"sha256:11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taming the Noise in Reinforcement Learning via Soft Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ari Pakman, Naftali Tishby, Roy Fox","submitted_at":"2015-12-28T23:59:12Z","abstract_excerpt":"Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias results from selecting, among several noisy estimates, the apparent optimum, which may actually be suboptimal. We propose G-learning, a new off-policy learning algorithm that regularizes the value estimates by penalizing deterministic policies in the beginning of the learning process. We show that this method reduces the bias of the value-function estimation, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.08562","kind":"arxiv","version":4},"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":"2026-05-18T00:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCi87nu5rumz54Db7EnHQJbB3OIAMcAaOU5YXbWVu9cw52iIccVNBMm6SMeV9P0yY7mT/Kq9G5iCvul+Ipb3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:19:27.340902Z"},"content_sha256":"989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815","schema_version":"1.0","event_id":"sha256:989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/bundle.json","state_url":"https://pith.science/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/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":"2026-06-05T16:19:27Z","links":{"resolver":"https://pith.science/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2","bundle":"https://pith.science/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/bundle.json","state":"https://pith.science/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOA5QNG3U2R3MSNHHC6ARRQAF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2","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":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3"},"schema_version":"1.0","source":{"id":"1512.08562","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"1512.08562v4","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"QOA5QNG3U2R3","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QOA5QNG3U2R3MSNH","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QOA5QNG3","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815","target":"graph","created_at":"2026-05-18T00:24:45Z","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":"Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias results from selecting, among several noisy estimates, the apparent optimum, which may actually be suboptimal. We propose G-learning, a new off-policy learning algorithm that regularizes the value estimates by penalizing deterministic policies in the beginning of the learning process. We show that this method reduces the bias of the value-function estimation, ","authors_text":"Ari Pakman, Naftali Tishby, Roy Fox","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title":"Taming the Noise in Reinforcement Learning via Soft Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.08562","kind":"arxiv","version":4},"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":"sha256:11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5","target":"record","created_at":"2026-05-18T00:24:45Z","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":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3"},"schema_version":"1.0","source":{"id":"1512.08562","kind":"arxiv","version":4}},"canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","first_computed_at":"2026-05-18T00:24:45.418249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:45.418249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYm6azdp8FCIs9ulC3TUhnAZ2mPc9nMRolyCYyBZe1cSocEEhaskwD67Bg8bJcveJl9VfWXHRIcfEhMPYGx9AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:45.418918Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.08562","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5","sha256:989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815"],"state_sha256":"3796fbb52f32bf335db12b460bb84f93f23d253642f2d0f25a1a706a56660b6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cq4Zk62d+cPkx7xmTyez7aOUd4M3nUd/BTAAFMCPkBNxtA+BJz5Z5AsB1WZ981RQOj3Sf5zXrKAhQadIc6jjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:19:27.342862Z","bundle_sha256":"15f5487ff50a5706e24c8b50ca73b1c37a27d960cd2021bab9abce30e778da11"}}