{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:72JD32B5MAAZAJT65YD75FTZFM","short_pith_number":"pith:72JD32B5","canonical_record":{"source":{"id":"1809.02112","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T17:39:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"367b741bd2d9d4cd74c2261c731bf2a7566ac4279baa5c549ad7ef59cff80678","abstract_canon_sha256":"b3609650b026832eab5a39bbef2e2bffd5bedcbdef2cb85925414bd9f72dedf4"},"schema_version":"1.0"},"canonical_sha256":"fe923de83d600190267eee07fe96792b344ba16f394271f9310f840340728fda","source":{"kind":"arxiv","id":"1809.02112","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02112","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02112v3","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02112","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"72JD32B5MAAZ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"72JD32B5MAAZAJT6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"72JD32B5","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:72JD32B5MAAZAJT65YD75FTZFM","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02112","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T17:39:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"367b741bd2d9d4cd74c2261c731bf2a7566ac4279baa5c549ad7ef59cff80678","abstract_canon_sha256":"b3609650b026832eab5a39bbef2e2bffd5bedcbdef2cb85925414bd9f72dedf4"},"schema_version":"1.0"},"canonical_sha256":"fe923de83d600190267eee07fe96792b344ba16f394271f9310f840340728fda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:52.901379Z","signature_b64":"Dn6/H49C6g+lgWha/9Tx5zMczyV6MqL8F7BVMNXECPpS5K6QihHZ2tQzPZrWh8IIN7vtZ85gli/k2EdY92DbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe923de83d600190267eee07fe96792b344ba16f394271f9310f840340728fda","last_reissued_at":"2026-05-18T00:01:52.900949Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:52.900949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02112","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQwhH8jl9N3HDY2XJemQv5Pt9oNj9/pq6+1p71tCYjX+WNVAZJddXJ7Mq8TYCDZ5N0tm/K5Z6avBJKCNxvYADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:03:54.390270Z"},"content_sha256":"6615f92197790d104572fc016e2c35625bd30804f2df95257ca8f959524c9613","schema_version":"1.0","event_id":"sha256:6615f92197790d104572fc016e2c35625bd30804f2df95257ca8f959524c9613"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:72JD32B5MAAZAJT65YD75FTZFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan-Yun Sun, Shou-De Lin, Yen-Yu Chang, Yueh-Hua Wu","submitted_at":"2018-09-06T17:39:18Z","abstract_excerpt":"This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02112","kind":"arxiv","version":3},"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":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7LsXZdB1L9Pr+2wOV/baWAkPLyMKKi/gS7IOdqczZd+I7aVKIO51yUlV58sW19dMEoWxo5WfT5JDaEMKnmjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:03:54.390621Z"},"content_sha256":"f7088549f7244141fc1c2ee7f15aae6c00019282e42ff712df6c1705e77600c7","schema_version":"1.0","event_id":"sha256:f7088549f7244141fc1c2ee7f15aae6c00019282e42ff712df6c1705e77600c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72JD32B5MAAZAJT65YD75FTZFM/bundle.json","state_url":"https://pith.science/pith/72JD32B5MAAZAJT65YD75FTZFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72JD32B5MAAZAJT65YD75FTZFM/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":"2026-06-01T18:03:54Z","links":{"resolver":"https://pith.science/pith/72JD32B5MAAZAJT65YD75FTZFM","bundle":"https://pith.science/pith/72JD32B5MAAZAJT65YD75FTZFM/bundle.json","state":"https://pith.science/pith/72JD32B5MAAZAJT65YD75FTZFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72JD32B5MAAZAJT65YD75FTZFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:72JD32B5MAAZAJT65YD75FTZFM","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":"b3609650b026832eab5a39bbef2e2bffd5bedcbdef2cb85925414bd9f72dedf4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T17:39:18Z","title_canon_sha256":"367b741bd2d9d4cd74c2261c731bf2a7566ac4279baa5c549ad7ef59cff80678"},"schema_version":"1.0","source":{"id":"1809.02112","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02112","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02112v3","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02112","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"72JD32B5MAAZ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"72JD32B5MAAZAJT6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"72JD32B5","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:f7088549f7244141fc1c2ee7f15aae6c00019282e42ff712df6c1705e77600c7","target":"graph","created_at":"2026-05-18T00:01:52Z","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":"This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.","authors_text":"Fan-Yun Sun, Shou-De Lin, Yen-Yu Chang, Yueh-Hua Wu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T17:39:18Z","title":"ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02112","kind":"arxiv","version":3},"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":"sha256:6615f92197790d104572fc016e2c35625bd30804f2df95257ca8f959524c9613","target":"record","created_at":"2026-05-18T00:01:52Z","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":"b3609650b026832eab5a39bbef2e2bffd5bedcbdef2cb85925414bd9f72dedf4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T17:39:18Z","title_canon_sha256":"367b741bd2d9d4cd74c2261c731bf2a7566ac4279baa5c549ad7ef59cff80678"},"schema_version":"1.0","source":{"id":"1809.02112","kind":"arxiv","version":3}},"canonical_sha256":"fe923de83d600190267eee07fe96792b344ba16f394271f9310f840340728fda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe923de83d600190267eee07fe96792b344ba16f394271f9310f840340728fda","first_computed_at":"2026-05-18T00:01:52.900949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:52.900949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dn6/H49C6g+lgWha/9Tx5zMczyV6MqL8F7BVMNXECPpS5K6QihHZ2tQzPZrWh8IIN7vtZ85gli/k2EdY92DbBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:52.901379Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02112","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6615f92197790d104572fc016e2c35625bd30804f2df95257ca8f959524c9613","sha256:f7088549f7244141fc1c2ee7f15aae6c00019282e42ff712df6c1705e77600c7"],"state_sha256":"03fcbb6da1b68c6cb9832fd090cdc8374f764c87ae83c90d91301df725323c5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6sgsAJOf+MofTB3MJQHTIKD/zjqp8+yHXdgICn7TmPWfZi6wIwdq4Hh0/z8GDW/QgdqNUW1j2SXisg+FQQKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:03:54.392508Z","bundle_sha256":"288cbeaee284b5076a02dddc5bca6b435636ff1b745dbc384a72220742b777b6"}}