{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YF6A3CD5KJ5T3FV66PZN4N3Y4B","short_pith_number":"pith:YF6A3CD5","schema_version":"1.0","canonical_sha256":"c17c0d887d527b3d96bef3f2de3778e0463fa33a96eb6b0faa813ab9dfa1c665","source":{"kind":"arxiv","id":"2105.03495","version":1},"attestation_state":"computed","paper":{"title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Beyer, David Schlangen, Sharid Lo\\'aiciga","submitted_at":"2021-05-07T20:28:33Z","abstract_excerpt":"Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with world-knowledge. Do neural language models encode such constraints? We design an extendable set of test suites addressing different aspects of discourse and dialogue coherence. Unlike most previous coherence evaluation studies, we address specific linguistic devices beyond sentence order perturbations, allowing for a more fine-grained analysis of what constitutes c"},"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":"2105.03495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T20:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"e3805785927e05cb3129f58412d6fe531c8731f2dc4ba4d127e97467a43ca1a8","abstract_canon_sha256":"81febbc1bbc6b5c72d343ca54d63e3090ae61db91e65f5395838cbb7c83fbf01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:35.690532Z","signature_b64":"lVvYPrs1ttwJmbvJOYdEtPkZM8OC7GMlf8Jpt2tOo+5RgVEGAVEvnEmtAja36vzS9May+fQr7BX4n6OIJtp6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c17c0d887d527b3d96bef3f2de3778e0463fa33a96eb6b0faa813ab9dfa1c665","last_reissued_at":"2026-07-05T02:38:35.690118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:35.690118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Beyer, David Schlangen, Sharid Lo\\'aiciga","submitted_at":"2021-05-07T20:28:33Z","abstract_excerpt":"Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with world-knowledge. Do neural language models encode such constraints? We design an extendable set of test suites addressing different aspects of discourse and dialogue coherence. Unlike most previous coherence evaluation studies, we address specific linguistic devices beyond sentence order perturbations, allowing for a more fine-grained analysis of what constitutes c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03495","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/2105.03495/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":"2105.03495","created_at":"2026-07-05T02:38:35.690173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03495v1","created_at":"2026-07-05T02:38:35.690173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03495","created_at":"2026-07-05T02:38:35.690173+00:00"},{"alias_kind":"pith_short_12","alias_value":"YF6A3CD5KJ5T","created_at":"2026-07-05T02:38:35.690173+00:00"},{"alias_kind":"pith_short_16","alias_value":"YF6A3CD5KJ5T3FV6","created_at":"2026-07-05T02:38:35.690173+00:00"},{"alias_kind":"pith_short_8","alias_value":"YF6A3CD5","created_at":"2026-07-05T02:38:35.690173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01781","citing_title":"A comprehensive taxonomy of hallucinations in Large Language Models","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B","json":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B.json","graph_json":"https://pith.science/api/pith-number/YF6A3CD5KJ5T3FV66PZN4N3Y4B/graph.json","events_json":"https://pith.science/api/pith-number/YF6A3CD5KJ5T3FV66PZN4N3Y4B/events.json","paper":"https://pith.science/paper/YF6A3CD5"},"agent_actions":{"view_html":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B","download_json":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B.json","view_paper":"https://pith.science/paper/YF6A3CD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03495&json=true","fetch_graph":"https://pith.science/api/pith-number/YF6A3CD5KJ5T3FV66PZN4N3Y4B/graph.json","fetch_events":"https://pith.science/api/pith-number/YF6A3CD5KJ5T3FV66PZN4N3Y4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B/action/storage_attestation","attest_author":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B/action/author_attestation","sign_citation":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B/action/citation_signature","submit_replication":"https://pith.science/pith/YF6A3CD5KJ5T3FV66PZN4N3Y4B/action/replication_record"}},"created_at":"2026-07-05T02:38:35.690173+00:00","updated_at":"2026-07-05T02:38:35.690173+00:00"}