{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TYDCEVWOQDBK55QCE4FYWJNWIY","short_pith_number":"pith:TYDCEVWO","schema_version":"1.0","canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","source":{"kind":"arxiv","id":"1506.01057","version":2},"attestation_state":"computed","paper":{"title":"A Hierarchical Neural Autoencoder for Paragraphs and Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li, Minh-Thang Luong","submitted_at":"2015-06-02T20:53:53Z","abstract_excerpt":"Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Long-short term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entit"},"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":"1506.01057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"efa46d82f3aad2983c4a8281279c71f6d27ed34d3e8469cd69a638651273eaef","abstract_canon_sha256":"3ad79e283f23eef1517d3309af1c2bfa152d212a435657477c6888678891a27e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:52.291149Z","signature_b64":"kh/8SbjxL/c1CeOCr7MmSn3R8IR0cNcqtdfFRcuullyCKctu5WKb2fnM6lJdExeyD36aM0tQVoEUBwI9lwd0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","last_reissued_at":"2026-05-18T01:55:52.290731Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:52.290731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchical Neural Autoencoder for Paragraphs and Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li, Minh-Thang Luong","submitted_at":"2015-06-02T20:53:53Z","abstract_excerpt":"Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Long-short term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01057","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1506.01057","created_at":"2026-05-18T01:55:52.290803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.01057v2","created_at":"2026-05-18T01:55:52.290803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01057","created_at":"2026-05-18T01:55:52.290803+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYDCEVWOQDBK","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYDCEVWOQDBK55QC","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYDCEVWO","created_at":"2026-05-18T12:29:44.643036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.12213","citing_title":"On the notion of number in humans and machines","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06330","citing_title":"Ranking sentences from product description & bullets for better search","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08679","citing_title":"Recommender Systems with Heterogeneous Side Information","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05165","citing_title":"Interests Burn-down Diffusion Process for Personalized Collaborative Filtering","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY","json":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY.json","graph_json":"https://pith.science/api/pith-number/TYDCEVWOQDBK55QCE4FYWJNWIY/graph.json","events_json":"https://pith.science/api/pith-number/TYDCEVWOQDBK55QCE4FYWJNWIY/events.json","paper":"https://pith.science/paper/TYDCEVWO"},"agent_actions":{"view_html":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY","download_json":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY.json","view_paper":"https://pith.science/paper/TYDCEVWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.01057&json=true","fetch_graph":"https://pith.science/api/pith-number/TYDCEVWOQDBK55QCE4FYWJNWIY/graph.json","fetch_events":"https://pith.science/api/pith-number/TYDCEVWOQDBK55QCE4FYWJNWIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/action/storage_attestation","attest_author":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/action/author_attestation","sign_citation":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/action/citation_signature","submit_replication":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/action/replication_record"}},"created_at":"2026-05-18T01:55:52.290803+00:00","updated_at":"2026-05-18T01:55:52.290803+00:00"}