{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:F3H3BK6HNWN5HZFUJQM7HB2TCV","short_pith_number":"pith:F3H3BK6H","canonical_record":{"source":{"id":"1705.07461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:20:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"92d40e5d79597dbc40eecb62b83ba76415596396be92037bc5349d0d0dd4ab78","abstract_canon_sha256":"ef8df5fb2a78ab446dbe4350361f4023cd0cfae8eded269f146006411256be44"},"schema_version":"1.0"},"canonical_sha256":"2ecfb0abc76d9bd3e4b44c19f38753155f46a87a926860f51884ab07a2ec9490","source":{"kind":"arxiv","id":"1705.07461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07461","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07461v2","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07461","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"F3H3BK6HNWN5","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3H3BK6HNWN5HZFU","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3H3BK6H","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:F3H3BK6HNWN5HZFUJQM7HB2TCV","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:20:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"92d40e5d79597dbc40eecb62b83ba76415596396be92037bc5349d0d0dd4ab78","abstract_canon_sha256":"ef8df5fb2a78ab446dbe4350361f4023cd0cfae8eded269f146006411256be44"},"schema_version":"1.0"},"canonical_sha256":"2ecfb0abc76d9bd3e4b44c19f38753155f46a87a926860f51884ab07a2ec9490","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:28.843804Z","signature_b64":"8rK0YP5f2rTe/2fjbzoqg6NyvCZORxlY2fPH/p4qYL/eRalWnbuchzVDdJEcfFrIeQ4wtszyn4TpplS675sUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ecfb0abc76d9bd3e4b44c19f38753155f46a87a926860f51884ab07a2ec9490","last_reissued_at":"2026-05-18T00:31:28.843071Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:28.843071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07461","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":"2026-05-18T00:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4Q1ABxLWSQ8G3ATIc3sI7fTyunpXofI6XoIIKNPpAHMNAgsEfjlKyVVyBL6zS/8vrxik4xXQClhDEzWaobEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T08:15:38.432140Z"},"content_sha256":"d458997ebd4708190c60b78f4b743a6c5e5d24faa6175f91306d361a7c9ec430","schema_version":"1.0","event_id":"sha256:d458997ebd4708190c60b78f4b743a6c5e5d24faa6175f91306d361a7c9ec430"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:F3H3BK6HNWN5HZFUJQM7HB2TCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shallow Updates for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Aviv Tamar, Daniel J. Mankowitz, Nir Levine, Shie Mannor, Tom Zahavy","submitted_at":"2017-05-21T15:20:15Z","abstract_excerpt":"Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or policy. Batch reinforcement learning methods with linear representations, on the other hand, are more stable and require less hyper parameter tuning. Yet, substantial feature engineering is necessary to achieve good results. In this work we propose a hybrid approach -- the Least Squ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07461","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":"2026-05-18T00:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9QIgq2zsS/ICHmVsFkqdqmZmuPq5D3ItVWUGkJGe63yZudfC4RX3tTRSi4/HeSNnucZIaJoOYqGDyNnPVlCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T08:15:38.432531Z"},"content_sha256":"92f110a505f5461a82c9f55dadc8e612fc15edc28ea9056af56d32e81dd0ca13","schema_version":"1.0","event_id":"sha256:92f110a505f5461a82c9f55dadc8e612fc15edc28ea9056af56d32e81dd0ca13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/bundle.json","state_url":"https://pith.science/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/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":"2026-05-22T08:15:38Z","links":{"resolver":"https://pith.science/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV","bundle":"https://pith.science/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/bundle.json","state":"https://pith.science/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3H3BK6HNWN5HZFUJQM7HB2TCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F3H3BK6HNWN5HZFUJQM7HB2TCV","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":"ef8df5fb2a78ab446dbe4350361f4023cd0cfae8eded269f146006411256be44","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:20:15Z","title_canon_sha256":"92d40e5d79597dbc40eecb62b83ba76415596396be92037bc5349d0d0dd4ab78"},"schema_version":"1.0","source":{"id":"1705.07461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07461","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07461v2","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07461","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"F3H3BK6HNWN5","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3H3BK6HNWN5HZFU","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3H3BK6H","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:92f110a505f5461a82c9f55dadc8e612fc15edc28ea9056af56d32e81dd0ca13","target":"graph","created_at":"2026-05-18T00:31:28Z","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":"Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or policy. Batch reinforcement learning methods with linear representations, on the other hand, are more stable and require less hyper parameter tuning. Yet, substantial feature engineering is necessary to achieve good results. In this work we propose a hybrid approach -- the Least Squ","authors_text":"Aviv Tamar, Daniel J. Mankowitz, Nir Levine, Shie Mannor, Tom Zahavy","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:20:15Z","title":"Shallow Updates for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07461","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:d458997ebd4708190c60b78f4b743a6c5e5d24faa6175f91306d361a7c9ec430","target":"record","created_at":"2026-05-18T00:31:28Z","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":"ef8df5fb2a78ab446dbe4350361f4023cd0cfae8eded269f146006411256be44","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:20:15Z","title_canon_sha256":"92d40e5d79597dbc40eecb62b83ba76415596396be92037bc5349d0d0dd4ab78"},"schema_version":"1.0","source":{"id":"1705.07461","kind":"arxiv","version":2}},"canonical_sha256":"2ecfb0abc76d9bd3e4b44c19f38753155f46a87a926860f51884ab07a2ec9490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ecfb0abc76d9bd3e4b44c19f38753155f46a87a926860f51884ab07a2ec9490","first_computed_at":"2026-05-18T00:31:28.843071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:28.843071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8rK0YP5f2rTe/2fjbzoqg6NyvCZORxlY2fPH/p4qYL/eRalWnbuchzVDdJEcfFrIeQ4wtszyn4TpplS675sUDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:28.843804Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d458997ebd4708190c60b78f4b743a6c5e5d24faa6175f91306d361a7c9ec430","sha256:92f110a505f5461a82c9f55dadc8e612fc15edc28ea9056af56d32e81dd0ca13"],"state_sha256":"422b8362829086660eb72bfe0d5198dc827ec868e129819df3c89b141001285e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+rrJPvhw8TR0sXmRkRZbJOkpy/aA7KwzTjVcPZK7tFxmUZZWkgbEh9ZW1Su12clngap2UsROZGtHrMBiRJPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T08:15:38.435659Z","bundle_sha256":"1681ee06c96dd20db0fdc0c43c6f62ebbff04895930531e37cb6a7545500d0ed"}}