{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FYTDWY6IW2MEUQMY7AEZ2DMDCR","short_pith_number":"pith:FYTDWY6I","canonical_record":{"source":{"id":"1705.01346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T10:22:22Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"62186d39f2ee7e359a7e6361654d9894566c1219e3cd6cb0140286cce6106c50","abstract_canon_sha256":"acf3a969efe06cd75366214c73e4f8595a3ebef2c99839afc27b426731d36805"},"schema_version":"1.0"},"canonical_sha256":"2e263b63c8b6984a4198f8099d0d8314596b74f231d0c2862092b3a6f5abb610","source":{"kind":"arxiv","id":"1705.01346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01346","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01346v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01346","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"FYTDWY6IW2ME","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FYTDWY6IW2MEUQMY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FYTDWY6I","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FYTDWY6IW2MEUQMY7AEZ2DMDCR","target":"record","payload":{"canonical_record":{"source":{"id":"1705.01346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T10:22:22Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"62186d39f2ee7e359a7e6361654d9894566c1219e3cd6cb0140286cce6106c50","abstract_canon_sha256":"acf3a969efe06cd75366214c73e4f8595a3ebef2c99839afc27b426731d36805"},"schema_version":"1.0"},"canonical_sha256":"2e263b63c8b6984a4198f8099d0d8314596b74f231d0c2862092b3a6f5abb610","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:05.373266Z","signature_b64":"dzkIf/g9IRFCsBS4rCq/DLqByXdIrUcFdDxBH9Z3t96nozVTAhS/uOOh1c9ly/pUObOA8r+pNImVIxIVbDuKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e263b63c8b6984a4198f8099d0d8314596b74f231d0c2862092b3a6f5abb610","last_reissued_at":"2026-05-18T00:45:05.372607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:05.372607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.01346","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d1bwBaXUwneOv5VD2ihbR0qfKGG9mgqlVwZgjsdyZHv/zECNWkOM+7VpmHQBPlFgRmP7KYLFDriATZkgcY6rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:24:17.330429Z"},"content_sha256":"1dbc0ec85b9c423a68fa8fc44f8da2c5984821e133ee6c9739877950e4ac352c","schema_version":"1.0","event_id":"sha256:1dbc0ec85b9c423a68fa8fc44f8da2c5984821e133ee6c9739877950e4ac352c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FYTDWY6IW2MEUQMY7AEZ2DMDCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Going Wider: Recurrent Neural Network With Parallel Cells","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Danhao Zhu, Jiajun Chen, Si Shen, Xin-Yu Dai","submitted_at":"2017-05-03T10:22:22Z","abstract_excerpt":"Recurrent Neural Network (RNN) has been widely applied for sequence modeling. In RNN, the hidden states at current step are full connected to those at previous step, thus the influence from less related features at previous step may potentially decrease model's learning ability. We propose a simple technique called parallel cells (PCs) to enhance the learning ability of Recurrent Neural Network (RNN). In each layer, we run multiple small RNN cells rather than one single large cell. In this paper, we evaluate PCs on 2 tasks. On language modeling task on PTB (Penn Tree Bank), our model outperfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01346","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmtB/SeQpknD3HckjnkLS3gwyLRX8ZT6ZFXFhAnGBnac7X8juQ9hD71i2oOicc2ZRAtPoeI0MrGH+dQ//WQxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:24:17.331127Z"},"content_sha256":"5460cf7437173b5945fb77722229967595bd342845ba018f79155797a4ffdfa4","schema_version":"1.0","event_id":"sha256:5460cf7437173b5945fb77722229967595bd342845ba018f79155797a4ffdfa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/bundle.json","state_url":"https://pith.science/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/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":"2026-05-29T18:24:17Z","links":{"resolver":"https://pith.science/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR","bundle":"https://pith.science/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/bundle.json","state":"https://pith.science/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYTDWY6IW2MEUQMY7AEZ2DMDCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FYTDWY6IW2MEUQMY7AEZ2DMDCR","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":"acf3a969efe06cd75366214c73e4f8595a3ebef2c99839afc27b426731d36805","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T10:22:22Z","title_canon_sha256":"62186d39f2ee7e359a7e6361654d9894566c1219e3cd6cb0140286cce6106c50"},"schema_version":"1.0","source":{"id":"1705.01346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01346","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01346v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01346","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"FYTDWY6IW2ME","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FYTDWY6IW2MEUQMY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FYTDWY6I","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:5460cf7437173b5945fb77722229967595bd342845ba018f79155797a4ffdfa4","target":"graph","created_at":"2026-05-18T00:45:05Z","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 Network (RNN) has been widely applied for sequence modeling. In RNN, the hidden states at current step are full connected to those at previous step, thus the influence from less related features at previous step may potentially decrease model's learning ability. We propose a simple technique called parallel cells (PCs) to enhance the learning ability of Recurrent Neural Network (RNN). In each layer, we run multiple small RNN cells rather than one single large cell. In this paper, we evaluate PCs on 2 tasks. On language modeling task on PTB (Penn Tree Bank), our model outperfor","authors_text":"Danhao Zhu, Jiajun Chen, Si Shen, Xin-Yu Dai","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T10:22:22Z","title":"Going Wider: Recurrent Neural Network With Parallel Cells"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01346","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":"sha256:1dbc0ec85b9c423a68fa8fc44f8da2c5984821e133ee6c9739877950e4ac352c","target":"record","created_at":"2026-05-18T00:45:05Z","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":"acf3a969efe06cd75366214c73e4f8595a3ebef2c99839afc27b426731d36805","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T10:22:22Z","title_canon_sha256":"62186d39f2ee7e359a7e6361654d9894566c1219e3cd6cb0140286cce6106c50"},"schema_version":"1.0","source":{"id":"1705.01346","kind":"arxiv","version":1}},"canonical_sha256":"2e263b63c8b6984a4198f8099d0d8314596b74f231d0c2862092b3a6f5abb610","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e263b63c8b6984a4198f8099d0d8314596b74f231d0c2862092b3a6f5abb610","first_computed_at":"2026-05-18T00:45:05.372607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:05.372607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dzkIf/g9IRFCsBS4rCq/DLqByXdIrUcFdDxBH9Z3t96nozVTAhS/uOOh1c9ly/pUObOA8r+pNImVIxIVbDuKDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:05.373266Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.01346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dbc0ec85b9c423a68fa8fc44f8da2c5984821e133ee6c9739877950e4ac352c","sha256:5460cf7437173b5945fb77722229967595bd342845ba018f79155797a4ffdfa4"],"state_sha256":"a7d936e4df21d54c6c30dbd3f01d51adceae951eb7b177ff0d016036008748fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+0XWQk3afOOxFFOYcJnS0vVKWH3SfeHJlWRB3XpWvR1iYTiTQ6PAXynELPo5fjb7SV4bdqrPD8bws/Beq/AsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:24:17.335188Z","bundle_sha256":"206cd6b1edb3eeba8f2de55b74f1de253bbd470d2e5b95910422910cc40a6166"}}