{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JHKJZUJSSP7K7VK4K6XY4K3AIP","short_pith_number":"pith:JHKJZUJS","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"},"canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","source":{"kind":"arxiv","id":"2402.13583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13583","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13583v2","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13583","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"JHKJZUJSSP7K","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"JHKJZUJSSP7K7VK4","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"JHKJZUJS","created_at":"2026-07-05T07:48:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JHKJZUJSSP7K7VK4K6XY4K3AIP","target":"record","payload":{"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"},"canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","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"},"source_kind":"arxiv","source_id":"2402.13583","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0pynX9qKGGlA5Hw3eCPTRYDHAV5HYlvk9ymJNyCb9G0PU8+GxTFOgCSpLXCa4rUTjmxCKg9OIiUJMjE42iaiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:45:41.259313Z"},"content_sha256":"5c03381ccc2345187277254f4feee758ff98c10ea32d42722ac79a08d3078dcc","schema_version":"1.0","event_id":"sha256:5c03381ccc2345187277254f4feee758ff98c10ea32d42722ac79a08d3078dcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JHKJZUJSSP7K7VK4K6XY4K3AIP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyB310P3LKaZDtRS02QC7cDOpLs/VOwZ+XPZRvyg8h5A257T18hkA0cYIxIQX9NjyWV0Z+hoA3b8SMogFBKyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:45:41.259832Z"},"content_sha256":"992ab1df5b2ba57dbf1dfb1940c6b56b38bfa60854026fc5f91ca3339accad5e","schema_version":"1.0","event_id":"sha256:992ab1df5b2ba57dbf1dfb1940c6b56b38bfa60854026fc5f91ca3339accad5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/bundle.json","state_url":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T19:45:41Z","links":{"resolver":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP","bundle":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/bundle.json","state":"https://pith.science/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JHKJZUJSSP7K7VK4K6XY4K3AIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JHKJZUJSSP7K7VK4K6XY4K3AIP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8a1cf56f865664942c414393ac5bf0193f72264493f17f9c0fe81bd6bfff5386","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T07:27:18Z","title_canon_sha256":"a7ae226dee82aa719b2fabc6970687cdf651971a104ee594098d618761ed0eae"},"schema_version":"1.0","source":{"id":"2402.13583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13583","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13583v2","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13583","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"JHKJZUJSSP7K","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"JHKJZUJSSP7K7VK4","created_at":"2026-07-05T07:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"JHKJZUJS","created_at":"2026-07-05T07:48:04Z"}],"graph_snapshots":[{"event_id":"sha256:992ab1df5b2ba57dbf1dfb1940c6b56b38bfa60854026fc5f91ca3339accad5e","target":"graph","created_at":"2026-07-05T07:48:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.13583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Conghui He, Dahua Lin, Hang Yan, Kai Lv, Qipeng Guo, Xiaoran Liu, Xipeng Qiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T07:27:18Z","title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13583","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c03381ccc2345187277254f4feee758ff98c10ea32d42722ac79a08d3078dcc","target":"record","created_at":"2026-07-05T07:48:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8a1cf56f865664942c414393ac5bf0193f72264493f17f9c0fe81bd6bfff5386","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T07:27:18Z","title_canon_sha256":"a7ae226dee82aa719b2fabc6970687cdf651971a104ee594098d618761ed0eae"},"schema_version":"1.0","source":{"id":"2402.13583","kind":"arxiv","version":2}},"canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49d49cd13293feafd55c57af8e2b6043ceb6a9a0060900112c48bbd39565c3c4","first_computed_at":"2026-07-05T07:48:04.443755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:04.443755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dKgbiD3HZN3KfA/cHAWAKAV3qBplsKmPHCsemUhRkgIMGtSY6WFeiHqGKNAkm7QlqhLAygzsKsoCilJzLx4AAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:04.444185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c03381ccc2345187277254f4feee758ff98c10ea32d42722ac79a08d3078dcc","sha256:992ab1df5b2ba57dbf1dfb1940c6b56b38bfa60854026fc5f91ca3339accad5e"],"state_sha256":"9a1ae0598e67a6fbaffa219226319f636e964fe259544de23f5e135289fcd97f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DROQa3yxjqba9J1L8DR/aGJLMUyN5g+dIZgK47BTRdWPUmc2/DJGfoNc/2N+cORUA2ZuQZ/zlVlU1QzlY8EQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:45:41.265791Z","bundle_sha256":"8b4b29cdbbb741f662a38a50dbb27c0992f2acb3340f365943be9eae85a30536"}}