{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5GOXFCH5JBUJ5RK3MRBEVSXDJO","short_pith_number":"pith:5GOXFCH5","schema_version":"1.0","canonical_sha256":"e99d7288fd48689ec55b64424acae34b842e0b45790e1b95546255ee4a4f36ed","source":{"kind":"arxiv","id":"1611.02654","version":2},"attestation_state":"computed","paper":{"title":"Sentence Ordering and Coherence Modeling using Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dragomir Radev, Honglak Lee, Lajanugen Logeswaran","submitted_at":"2016-11-08T19:04:09Z","abstract_excerpt":"Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end unsupervised deep learning approach based on the set-to-sequence framework to address this problem. Our model strongly outperforms prior methods in the order discrimination task and a novel task of ordering abstracts from scientific articles. Furthermore, our work shows that useful text representations can be obtained by learning to order sentences. Visualizing the l"},"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":"1611.02654","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-08T19:04:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3fcf4bf77792e3a3cf2bdee19f712d3680bf92760b06194c36abf69862dcad2d","abstract_canon_sha256":"09544b599371c578e25ca8257dadc878da7920a4f49204e0ff9ca523c7041859"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:28.380213Z","signature_b64":"PABu6ro8zT008SnvQ2vSsCw713OLxXVJ2IXk/fyu5klVdPN7pd9JesYKouNw5vCRWj/UW8twuSFrQaPtqe4zCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e99d7288fd48689ec55b64424acae34b842e0b45790e1b95546255ee4a4f36ed","last_reissued_at":"2026-05-18T00:27:28.379389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:28.379389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence Ordering and Coherence Modeling using Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dragomir Radev, Honglak Lee, Lajanugen Logeswaran","submitted_at":"2016-11-08T19:04:09Z","abstract_excerpt":"Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end unsupervised deep learning approach based on the set-to-sequence framework to address this problem. Our model strongly outperforms prior methods in the order discrimination task and a novel task of ordering abstracts from scientific articles. Furthermore, our work shows that useful text representations can be obtained by learning to order sentences. Visualizing the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02654","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":"1611.02654","created_at":"2026-05-18T00:27:28.379537+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02654v2","created_at":"2026-05-18T00:27:28.379537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02654","created_at":"2026-05-18T00:27:28.379537+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GOXFCH5JBUJ","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GOXFCH5JBUJ5RK3","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GOXFCH5","created_at":"2026-05-18T12:30:01.593930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00142","citing_title":"Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO","json":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO.json","graph_json":"https://pith.science/api/pith-number/5GOXFCH5JBUJ5RK3MRBEVSXDJO/graph.json","events_json":"https://pith.science/api/pith-number/5GOXFCH5JBUJ5RK3MRBEVSXDJO/events.json","paper":"https://pith.science/paper/5GOXFCH5"},"agent_actions":{"view_html":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO","download_json":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO.json","view_paper":"https://pith.science/paper/5GOXFCH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02654&json=true","fetch_graph":"https://pith.science/api/pith-number/5GOXFCH5JBUJ5RK3MRBEVSXDJO/graph.json","fetch_events":"https://pith.science/api/pith-number/5GOXFCH5JBUJ5RK3MRBEVSXDJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO/action/storage_attestation","attest_author":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO/action/author_attestation","sign_citation":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO/action/citation_signature","submit_replication":"https://pith.science/pith/5GOXFCH5JBUJ5RK3MRBEVSXDJO/action/replication_record"}},"created_at":"2026-05-18T00:27:28.379537+00:00","updated_at":"2026-05-18T00:27:28.379537+00:00"}