{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JHKJZUJSSP7K7VK4K6XY4K3AIP","short_pith_number":"pith:JHKJZUJS","schema_version":"1.0","canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","source":{"kind":"arxiv","id":"2402.13583","version":2},"attestation_state":"computed","paper":{"title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui He, Dahua Lin, Hang Yan, Kai Lv, Qipeng Guo, Xiaoran Liu, Xipeng Qiu","submitted_at":"2024-02-21T07:27:18Z","abstract_excerpt":"The quality of training data are crucial for enhancing the long-text capabilities of foundation models. Despite existing efforts to refine data quality through heuristic rules and evaluations based on data diversity and difficulty, there's a lack of systematic approaches specifically tailored for assessing long texts. Addressing this gap, our work systematically measures the quality of long texts by evaluating three fundamental linguistic dimensions: coherence, cohesion, and complexity. Drawing inspiration from the aforementioned three dimensions, we introduce a suite of metrics designed to ev"},"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":"2402.13583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T07:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"a7ae226dee82aa719b2fabc6970687cdf651971a104ee594098d618761ed0eae","abstract_canon_sha256":"8a1cf56f865664942c414393ac5bf0193f72264493f17f9c0fe81bd6bfff5386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:04.444185Z","signature_b64":"dKgbiD3HZN3KfA/cHAWAKAV3qBplsKmPHCsemUhRkgIMGtSY6WFeiHqGKNAkm7QlqhLAygzsKsoCilJzLx4AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","last_reissued_at":"2026-07-05T07:48:04.443755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:04.443755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui He, Dahua Lin, Hang Yan, Kai Lv, Qipeng Guo, Xiaoran Liu, Xipeng Qiu","submitted_at":"2024-02-21T07:27:18Z","abstract_excerpt":"The quality of training data are crucial for enhancing the long-text capabilities of foundation models. Despite existing efforts to refine data quality through heuristic rules and evaluations based on data diversity and difficulty, there's a lack of systematic approaches specifically tailored for assessing long texts. Addressing this gap, our work systematically measures the quality of long texts by evaluating three fundamental linguistic dimensions: coherence, cohesion, and complexity. Drawing inspiration from the aforementioned three dimensions, we introduce a suite of metrics designed to ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13583","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.13583/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":"2402.13583","created_at":"2026-07-05T07:48:04.443812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13583v2","created_at":"2026-07-05T07:48:04.443812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13583","created_at":"2026-07-05T07:48:04.443812+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHKJZUJSSP7K","created_at":"2026-07-05T07:48:04.443812+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHKJZUJSSP7K7VK4","created_at":"2026-07-05T07:48:04.443812+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHKJZUJS","created_at":"2026-07-05T07:48:04.443812+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/JHKJZUJSSP7K7VK4K6XY4K3AIP","json":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP.json","graph_json":"https://pith.science/api/pith-number/JHKJZUJSSP7K7VK4K6XY4K3AIP/graph.json","events_json":"https://pith.science/api/pith-number/JHKJZUJSSP7K7VK4K6XY4K3AIP/events.json","paper":"https://pith.science/paper/JHKJZUJS"},"agent_actions":{"view_html":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP","download_json":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP.json","view_paper":"https://pith.science/paper/JHKJZUJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13583&json=true","fetch_graph":"https://pith.science/api/pith-number/JHKJZUJSSP7K7VK4K6XY4K3AIP/graph.json","fetch_events":"https://pith.science/api/pith-number/JHKJZUJSSP7K7VK4K6XY4K3AIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/action/storage_attestation","attest_author":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/action/author_attestation","sign_citation":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/action/citation_signature","submit_replication":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/action/replication_record"}},"created_at":"2026-07-05T07:48:04.443812+00:00","updated_at":"2026-07-05T07:48:04.443812+00:00"}