{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RSHBMXOCY5N6OTHKHAUOX7ZUW5","short_pith_number":"pith:RSHBMXOC","schema_version":"1.0","canonical_sha256":"8c8e165dc2c75be74cea3828ebff34b75fd70c5e94335ca65b779746d0a107d8","source":{"kind":"arxiv","id":"1909.00349","version":1},"attestation_state":"computed","paper":{"title":"A Unified Neural Coherence Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Han Cheol Moon, Shafiq Joty, Tasnim Mohiuddin, Xu Chi","submitted_at":"2019-09-01T08:16:53Z","abstract_excerpt":"Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural"},"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":"1909.00349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-01T08:16:53Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d15cc0048c0a4d80f0cc0ca04508b1eb1814ce7e730df6b662ada6df37992667","abstract_canon_sha256":"369cf61d146859608f64628cf887dc42ed08cb64f4ca60df9e715ccab1e9042e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:08.211728Z","signature_b64":"9wHHCFEoYTPmx9IafxcrxSuneizupSMDm35Sk1fAOxr8ejxrczi3HK3pjWLnbtjh677Baux/blw4gNJJz5/6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8e165dc2c75be74cea3828ebff34b75fd70c5e94335ca65b779746d0a107d8","last_reissued_at":"2026-07-05T00:01:08.211351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:08.211351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Neural Coherence Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Han Cheol Moon, Shafiq Joty, Tasnim Mohiuddin, Xu Chi","submitted_at":"2019-09-01T08:16:53Z","abstract_excerpt":"Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00349","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.00349/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.00349","created_at":"2026-07-05T00:01:08.211411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00349v1","created_at":"2026-07-05T00:01:08.211411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00349","created_at":"2026-07-05T00:01:08.211411+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSHBMXOCY5N6","created_at":"2026-07-05T00:01:08.211411+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSHBMXOCY5N6OTHK","created_at":"2026-07-05T00:01:08.211411+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSHBMXOC","created_at":"2026-07-05T00:01:08.211411+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/RSHBMXOCY5N6OTHKHAUOX7ZUW5","json":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5.json","graph_json":"https://pith.science/api/pith-number/RSHBMXOCY5N6OTHKHAUOX7ZUW5/graph.json","events_json":"https://pith.science/api/pith-number/RSHBMXOCY5N6OTHKHAUOX7ZUW5/events.json","paper":"https://pith.science/paper/RSHBMXOC"},"agent_actions":{"view_html":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5","download_json":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5.json","view_paper":"https://pith.science/paper/RSHBMXOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00349&json=true","fetch_graph":"https://pith.science/api/pith-number/RSHBMXOCY5N6OTHKHAUOX7ZUW5/graph.json","fetch_events":"https://pith.science/api/pith-number/RSHBMXOCY5N6OTHKHAUOX7ZUW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5/action/storage_attestation","attest_author":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5/action/author_attestation","sign_citation":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5/action/citation_signature","submit_replication":"https://pith.science/pith/RSHBMXOCY5N6OTHKHAUOX7ZUW5/action/replication_record"}},"created_at":"2026-07-05T00:01:08.211411+00:00","updated_at":"2026-07-05T00:01:08.211411+00:00"}