{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DII6VXE4XZCKW55INT27LM7RVU","short_pith_number":"pith:DII6VXE4","schema_version":"1.0","canonical_sha256":"1a11eadc9cbe44ab77a86cf5f5b3f1ad009ca4c545ff67880d7b869f79eac282","source":{"kind":"arxiv","id":"1811.00511","version":2},"attestation_state":"computed","paper":{"title":"Towards Coherent and Cohesive Long-form Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Brockett, Jianfeng Gao, Mengdi Wang, Michel Galley, Pengchuan Zhang, Woon Sang Cho, Xiujun Li, Yizhe Zhang","submitted_at":"2018-11-01T17:30:50Z","abstract_excerpt":"Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models from the perspectives of coherence and cohesion. In this work, we propose a new neural language model that is equipped with two neural discriminators which provide feedback signals at the levels of sentence (cohesion) and paragraph (coherence). Our model is trained using a simple yet efficient variant of policy gradient, called negative-critical sequence traini"},"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":"1811.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T17:30:50Z","cross_cats_sorted":[],"title_canon_sha256":"49d371a88df8ff6fa30c2392c819a2bcc5d5190dd098072ebed537db6aea403c","abstract_canon_sha256":"c9b03cd2ebef67e2bd6c1974b13927d1d3b6ad88a849a205585409204e517d9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.940764Z","signature_b64":"zXiiMyMV1AYlGa0CWdRhjLeLPJouOx48X39WFOtBGm4syxPf7RQ174TobF5W7yAZgdIuVlKs8cvr5L1qR4aCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a11eadc9cbe44ab77a86cf5f5b3f1ad009ca4c545ff67880d7b869f79eac282","last_reissued_at":"2026-05-17T23:44:47.940162Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.940162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Coherent and Cohesive Long-form Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Brockett, Jianfeng Gao, Mengdi Wang, Michel Galley, Pengchuan Zhang, Woon Sang Cho, Xiujun Li, Yizhe Zhang","submitted_at":"2018-11-01T17:30:50Z","abstract_excerpt":"Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models from the perspectives of coherence and cohesion. In this work, we propose a new neural language model that is equipped with two neural discriminators which provide feedback signals at the levels of sentence (cohesion) and paragraph (coherence). Our model is trained using a simple yet efficient variant of policy gradient, called negative-critical sequence traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00511","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":"1811.00511","created_at":"2026-05-17T23:44:47.940237+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00511v2","created_at":"2026-05-17T23:44:47.940237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00511","created_at":"2026-05-17T23:44:47.940237+00:00"},{"alias_kind":"pith_short_12","alias_value":"DII6VXE4XZCK","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DII6VXE4XZCKW55I","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DII6VXE4","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2009.01325","citing_title":"Learning to summarize from human feedback","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU","json":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU.json","graph_json":"https://pith.science/api/pith-number/DII6VXE4XZCKW55INT27LM7RVU/graph.json","events_json":"https://pith.science/api/pith-number/DII6VXE4XZCKW55INT27LM7RVU/events.json","paper":"https://pith.science/paper/DII6VXE4"},"agent_actions":{"view_html":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU","download_json":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU.json","view_paper":"https://pith.science/paper/DII6VXE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00511&json=true","fetch_graph":"https://pith.science/api/pith-number/DII6VXE4XZCKW55INT27LM7RVU/graph.json","fetch_events":"https://pith.science/api/pith-number/DII6VXE4XZCKW55INT27LM7RVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU/action/storage_attestation","attest_author":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU/action/author_attestation","sign_citation":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU/action/citation_signature","submit_replication":"https://pith.science/pith/DII6VXE4XZCKW55INT27LM7RVU/action/replication_record"}},"created_at":"2026-05-17T23:44:47.940237+00:00","updated_at":"2026-05-17T23:44:47.940237+00:00"}