{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5HG6PDZ7YG34VYHX2PNAOE67FG","short_pith_number":"pith:5HG6PDZ7","canonical_record":{"source":{"id":"1805.09238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T15:53:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"edfa2d4c8c4326615328b11c228cddc956c780c6b76cc6eb5f8802349525766b","abstract_canon_sha256":"aaccb7c0dcdf0f6f4f02a1a636c7b548c39649f134cc3d97a5fbf7b6c2b4282a"},"schema_version":"1.0"},"canonical_sha256":"e9cde78f3fc1b7cae0f7d3da0713df2986c923ea526cd8992b5b28992d73ac1c","source":{"kind":"arxiv","id":"1805.09238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09238","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09238v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09238","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"5HG6PDZ7YG34","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5HG6PDZ7YG34VYHX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5HG6PDZ7","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5HG6PDZ7YG34VYHX2PNAOE67FG","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T15:53:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"edfa2d4c8c4326615328b11c228cddc956c780c6b76cc6eb5f8802349525766b","abstract_canon_sha256":"aaccb7c0dcdf0f6f4f02a1a636c7b548c39649f134cc3d97a5fbf7b6c2b4282a"},"schema_version":"1.0"},"canonical_sha256":"e9cde78f3fc1b7cae0f7d3da0713df2986c923ea526cd8992b5b28992d73ac1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:08.186467Z","signature_b64":"o1I9/SZYlCuf0VVCmNQjzMKjy+B0s5Q+BO5DGe7DgjrPf7M7BVoxnv3BZC++Mb13wK22aVokgji/lSPI7WWYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9cde78f3fc1b7cae0f7d3da0713df2986c923ea526cd8992b5b28992d73ac1c","last_reissued_at":"2026-05-18T00:15:08.185941Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:08.185941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09238","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":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTwh2a2Thqp07y8ntcBv3xnSnFwdf+WtmFcDC/D1rYKZPAp8tPJZzQXrMFd5SQEgUc2bJjkm0Zz8IRZ2XZrMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:15:34.902133Z"},"content_sha256":"063962f40a0715d08d3a686f3eff2a0f44d9bbae4761818f7b7c06fa4bdfefc3","schema_version":"1.0","event_id":"sha256:063962f40a0715d08d3a686f3eff2a0f44d9bbae4761818f7b7c06fa4bdfefc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5HG6PDZ7YG34VYHX2PNAOE67FG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highway State Gating for Recurrent Highway Networks: improving information flow through time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Haim Permuter, Ron Shoham","submitted_at":"2018-05-23T15:53:10Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models are structured with a transition depth of 2-4 layers. Recurrent Highway Networks (RHNs) were introduced in order to tackle this issue. These have achieved state-of-the-art performance on a few benchmarks using a depth of 10 layers. However, the performance of this architecture suffers from a bottleneck, and ceases to improve when an attempt is made to add mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09238","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":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0tQ1M9bwk2ArQ5D1VjJs5YcEadbqIonsa6du//AdEE5Bd+hJlojshUdDElPCv7i48VdcDpX3SADGX41bBqueAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:15:34.902843Z"},"content_sha256":"a4093d5798b864aafba2e1ce1a35c5950630073aff5f84d5e48adebeea22860b","schema_version":"1.0","event_id":"sha256:a4093d5798b864aafba2e1ce1a35c5950630073aff5f84d5e48adebeea22860b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/bundle.json","state_url":"https://pith.science/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/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":"2026-05-31T21:15:34Z","links":{"resolver":"https://pith.science/pith/5HG6PDZ7YG34VYHX2PNAOE67FG","bundle":"https://pith.science/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/bundle.json","state":"https://pith.science/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HG6PDZ7YG34VYHX2PNAOE67FG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5HG6PDZ7YG34VYHX2PNAOE67FG","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":"aaccb7c0dcdf0f6f4f02a1a636c7b548c39649f134cc3d97a5fbf7b6c2b4282a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T15:53:10Z","title_canon_sha256":"edfa2d4c8c4326615328b11c228cddc956c780c6b76cc6eb5f8802349525766b"},"schema_version":"1.0","source":{"id":"1805.09238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09238","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09238v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09238","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"5HG6PDZ7YG34","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5HG6PDZ7YG34VYHX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5HG6PDZ7","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:a4093d5798b864aafba2e1ce1a35c5950630073aff5f84d5e48adebeea22860b","target":"graph","created_at":"2026-05-18T00:15:08Z","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":"Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models are structured with a transition depth of 2-4 layers. Recurrent Highway Networks (RHNs) were introduced in order to tackle this issue. These have achieved state-of-the-art performance on a few benchmarks using a depth of 10 layers. However, the performance of this architecture suffers from a bottleneck, and ceases to improve when an attempt is made to add mor","authors_text":"Haim Permuter, Ron Shoham","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T15:53:10Z","title":"Highway State Gating for Recurrent Highway Networks: improving information flow through time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09238","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":"sha256:063962f40a0715d08d3a686f3eff2a0f44d9bbae4761818f7b7c06fa4bdfefc3","target":"record","created_at":"2026-05-18T00:15:08Z","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":"aaccb7c0dcdf0f6f4f02a1a636c7b548c39649f134cc3d97a5fbf7b6c2b4282a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T15:53:10Z","title_canon_sha256":"edfa2d4c8c4326615328b11c228cddc956c780c6b76cc6eb5f8802349525766b"},"schema_version":"1.0","source":{"id":"1805.09238","kind":"arxiv","version":1}},"canonical_sha256":"e9cde78f3fc1b7cae0f7d3da0713df2986c923ea526cd8992b5b28992d73ac1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9cde78f3fc1b7cae0f7d3da0713df2986c923ea526cd8992b5b28992d73ac1c","first_computed_at":"2026-05-18T00:15:08.185941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:08.185941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1I9/SZYlCuf0VVCmNQjzMKjy+B0s5Q+BO5DGe7DgjrPf7M7BVoxnv3BZC++Mb13wK22aVokgji/lSPI7WWYBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:08.186467Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:063962f40a0715d08d3a686f3eff2a0f44d9bbae4761818f7b7c06fa4bdfefc3","sha256:a4093d5798b864aafba2e1ce1a35c5950630073aff5f84d5e48adebeea22860b"],"state_sha256":"4cf7d4e860892bb243c3eb11a7fe0329a1698182a8dd4e9d6f07e923cdcbf3e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXMk2qQSJlvFsS+RlqGGVWCOlQedlP+0ZktrjsYkYpWkiOhLsKnSlSLnJs6D32fj7AIZjR11jX48bRNc77GrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T21:15:34.906700Z","bundle_sha256":"f48c8ccf3f8d1ad8837d7316c3b6116f9cd3650df65e7fc4a13ca3b045aeb394"}}