{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GGNQFF7JMS2I2FECLAYMAPVMI5","short_pith_number":"pith:GGNQFF7J","schema_version":"1.0","canonical_sha256":"319b0297e964b48d14825830c03eac474ce259b1bca1de5f1505907e61ad121e","source":{"kind":"arxiv","id":"1808.09522","version":1},"attestation_state":"computed","paper":{"title":"Layer Trajectory LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changliang Liu, Jinyu Li, Yifan Gong","submitted_at":"2018-08-28T20:13:18Z","abstract_excerpt":"It is popular to stack LSTM layers to get better modeling power, especially when large amount of training data is available. However, an LSTM-RNN with too many vanilla LSTM layers is very hard to train and there still exists the gradient vanishing issue if the network goes too deep. This issue can be partially solved by adding skip connections between layers, such as residual LSTM. In this paper, we propose a layer trajectory LSTM (ltLSTM) which builds a layer-LSTM using all the layer outputs from a standard multi-layer time-LSTM. This layer-LSTM scans the outputs from time-LSTMs, and uses the"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1808.09522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T20:13:18Z","cross_cats_sorted":[],"title_canon_sha256":"ccf550e736e9787a73725a0638be40c2e4be620b240e5ce18e694f8e45004710","abstract_canon_sha256":"f472d2a0be97561e6b6aae291e184dc2f7c9e4cad12e6f91f95a53a9fc67cd13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.304718Z","signature_b64":"shY0VLjScmIIPIREFvoo0uL6cRLi03UsCwmodev4sSOA2QzNYKYET2mZPFC6466i448CyenJUgQuccHvl20mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"319b0297e964b48d14825830c03eac474ce259b1bca1de5f1505907e61ad121e","last_reissued_at":"2026-05-18T00:06:55.304029Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.304029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer Trajectory LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changliang Liu, Jinyu Li, Yifan Gong","submitted_at":"2018-08-28T20:13:18Z","abstract_excerpt":"It is popular to stack LSTM layers to get better modeling power, especially when large amount of training data is available. However, an LSTM-RNN with too many vanilla LSTM layers is very hard to train and there still exists the gradient vanishing issue if the network goes too deep. This issue can be partially solved by adding skip connections between layers, such as residual LSTM. In this paper, we propose a layer trajectory LSTM (ltLSTM) which builds a layer-LSTM using all the layer outputs from a standard multi-layer time-LSTM. This layer-LSTM scans the outputs from time-LSTMs, and uses the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09522","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1808.09522","created_at":"2026-05-18T00:06:55.304126+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09522v1","created_at":"2026-05-18T00:06:55.304126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09522","created_at":"2026-05-18T00:06:55.304126+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGNQFF7JMS2I","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGNQFF7JMS2I2FEC","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGNQFF7J","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5","json":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5.json","graph_json":"https://pith.science/api/pith-number/GGNQFF7JMS2I2FECLAYMAPVMI5/graph.json","events_json":"https://pith.science/api/pith-number/GGNQFF7JMS2I2FECLAYMAPVMI5/events.json","paper":"https://pith.science/paper/GGNQFF7J"},"agent_actions":{"view_html":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5","download_json":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5.json","view_paper":"https://pith.science/paper/GGNQFF7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09522&json=true","fetch_graph":"https://pith.science/api/pith-number/GGNQFF7JMS2I2FECLAYMAPVMI5/graph.json","fetch_events":"https://pith.science/api/pith-number/GGNQFF7JMS2I2FECLAYMAPVMI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5/action/storage_attestation","attest_author":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5/action/author_attestation","sign_citation":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5/action/citation_signature","submit_replication":"https://pith.science/pith/GGNQFF7JMS2I2FECLAYMAPVMI5/action/replication_record"}},"created_at":"2026-05-18T00:06:55.304126+00:00","updated_at":"2026-05-18T00:06:55.304126+00:00"}