{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BBPYTXEKOXD3RADEOGHVCAPV7P","short_pith_number":"pith:BBPYTXEK","canonical_record":{"source":{"id":"1805.07476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T23:35:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0ced4e648f1b33a1c7bf9bd751c55f1326bcd81cbe5a392374fea16cacaadc2b","abstract_canon_sha256":"2795dabfca97aaca10b28745d0a924f4cbf68b02fa4ffa4bbf76d1570fc4904e"},"schema_version":"1.0"},"canonical_sha256":"085f89dc8a75c7b88064718f5101f5fbfa03203566df94a2fddd7f5f0723b1ec","source":{"kind":"arxiv","id":"1805.07476","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07476","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07476v2","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07476","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"BBPYTXEKOXD3","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBPYTXEKOXD3RADE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBPYTXEK","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BBPYTXEKOXD3RADEOGHVCAPV7P","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T23:35:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0ced4e648f1b33a1c7bf9bd751c55f1326bcd81cbe5a392374fea16cacaadc2b","abstract_canon_sha256":"2795dabfca97aaca10b28745d0a924f4cbf68b02fa4ffa4bbf76d1570fc4904e"},"schema_version":"1.0"},"canonical_sha256":"085f89dc8a75c7b88064718f5101f5fbfa03203566df94a2fddd7f5f0723b1ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:20.238928Z","signature_b64":"vrYA/sp3/FQpFzjAWUmqJk2gLRjhxTnN2dgyNDfIEqR4NdizJEg6z7aMDFd6LFW4JvGHx7TSbkgSCzDWCmRnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085f89dc8a75c7b88064718f5101f5fbfa03203566df94a2fddd7f5f0723b1ec","last_reissued_at":"2026-05-18T00:06:20.238222Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:20.238222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07476","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":"2026-05-18T00:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NH3UefQYZbzp0N0Ez7W5wyWIRco1g79LIwsA/j0ZJIv/99TePss1htlXkFnKpVu4QoN5/qWSRnKHznzpaiFYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:31:41.919611Z"},"content_sha256":"463eba9b5295b089ad0d78e0e68570fdce7384855d465a535f83f00deb249926","schema_version":"1.0","event_id":"sha256:463eba9b5295b089ad0d78e0e68570fdce7384855d465a535f83f00deb249926"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BBPYTXEKOXD3RADEOGHVCAPV7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two geometric input transformation methods for fast online reinforcement learning with neural nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Banafsheh Rafiee, Huizhen Yu, Richard S. Sutton, Sina Ghiassian","submitted_at":"2018-05-18T23:35:14Z","abstract_excerpt":"We apply neural nets with ReLU gates in online reinforcement learning. Our goal is to train these networks in an incremental manner, without the computationally expensive experience replay. By studying how individual neural nodes behave in online training, we recognize that the global nature of ReLU gates can cause undesirable learning interference in each node's learning behavior. We propose reducing such interferences with two efficient input transformation methods that are geometric in nature and match well the geometric property of ReLU gates. The first one is tile coding, a classic binary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07476","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":"2026-05-18T00:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RKzQVjLHJxHdsANot6vqJ+ngxG6rsHUMASlx2o4FBL0MrKS9RGkIzsx9dZrUPIh8Nt39G4u5cLgwVhKhxpKcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:31:41.920373Z"},"content_sha256":"28a18bf2b98bbb6ad3f1d2e9e62984d199bc9c5d089be59c7a685d9a38ea5598","schema_version":"1.0","event_id":"sha256:28a18bf2b98bbb6ad3f1d2e9e62984d199bc9c5d089be59c7a685d9a38ea5598"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/bundle.json","state_url":"https://pith.science/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/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":"2026-05-31T16:31:41Z","links":{"resolver":"https://pith.science/pith/BBPYTXEKOXD3RADEOGHVCAPV7P","bundle":"https://pith.science/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/bundle.json","state":"https://pith.science/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBPYTXEKOXD3RADEOGHVCAPV7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BBPYTXEKOXD3RADEOGHVCAPV7P","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":"2795dabfca97aaca10b28745d0a924f4cbf68b02fa4ffa4bbf76d1570fc4904e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T23:35:14Z","title_canon_sha256":"0ced4e648f1b33a1c7bf9bd751c55f1326bcd81cbe5a392374fea16cacaadc2b"},"schema_version":"1.0","source":{"id":"1805.07476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07476","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07476v2","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07476","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"BBPYTXEKOXD3","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBPYTXEKOXD3RADE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBPYTXEK","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:28a18bf2b98bbb6ad3f1d2e9e62984d199bc9c5d089be59c7a685d9a38ea5598","target":"graph","created_at":"2026-05-18T00:06:20Z","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 apply neural nets with ReLU gates in online reinforcement learning. Our goal is to train these networks in an incremental manner, without the computationally expensive experience replay. By studying how individual neural nodes behave in online training, we recognize that the global nature of ReLU gates can cause undesirable learning interference in each node's learning behavior. We propose reducing such interferences with two efficient input transformation methods that are geometric in nature and match well the geometric property of ReLU gates. The first one is tile coding, a classic binary","authors_text":"Banafsheh Rafiee, Huizhen Yu, Richard S. Sutton, Sina Ghiassian","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T23:35:14Z","title":"Two geometric input transformation methods for fast online reinforcement learning with neural nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07476","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":"sha256:463eba9b5295b089ad0d78e0e68570fdce7384855d465a535f83f00deb249926","target":"record","created_at":"2026-05-18T00:06:20Z","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":"2795dabfca97aaca10b28745d0a924f4cbf68b02fa4ffa4bbf76d1570fc4904e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T23:35:14Z","title_canon_sha256":"0ced4e648f1b33a1c7bf9bd751c55f1326bcd81cbe5a392374fea16cacaadc2b"},"schema_version":"1.0","source":{"id":"1805.07476","kind":"arxiv","version":2}},"canonical_sha256":"085f89dc8a75c7b88064718f5101f5fbfa03203566df94a2fddd7f5f0723b1ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"085f89dc8a75c7b88064718f5101f5fbfa03203566df94a2fddd7f5f0723b1ec","first_computed_at":"2026-05-18T00:06:20.238222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:20.238222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrYA/sp3/FQpFzjAWUmqJk2gLRjhxTnN2dgyNDfIEqR4NdizJEg6z7aMDFd6LFW4JvGHx7TSbkgSCzDWCmRnCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:20.238928Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:463eba9b5295b089ad0d78e0e68570fdce7384855d465a535f83f00deb249926","sha256:28a18bf2b98bbb6ad3f1d2e9e62984d199bc9c5d089be59c7a685d9a38ea5598"],"state_sha256":"a4b5f1dd10087ec76565f4e61057c836176326fd5c13883cc706ac96a640732a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdFc8C9FG6HacPZ2S5V9GYT8lGmZ1VkH2Y1CT11wSwBhkQVrzFv9Niv1zXG+Rqv8m5K25vzrszhesDiLVEAwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:31:41.924298Z","bundle_sha256":"60afad3a7cc953b575aec50efea03bd6c839084fd9189f91316dec6d3b3cae57"}}