{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TIPU6ITY5L5NY5PCMGOQAIPVEK","short_pith_number":"pith:TIPU6ITY","canonical_record":{"source":{"id":"2404.09002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T13:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"423079aa5377ce6f54a7722df3c8ca9db6fda4002dc4c0a70b884f21d0fa6096","abstract_canon_sha256":"4fc1aa1ef59656bb7a86c8028cc88522cffe0ae0b9670033193b62e1546ffeca"},"schema_version":"1.0"},"canonical_sha256":"9a1f4f2278eafadc75e2619d0021f522872ee78521e2c64ece2926e1193b4c58","source":{"kind":"arxiv","id":"2404.09002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09002","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09002v1","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09002","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"TIPU6ITY5L5N","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"TIPU6ITY5L5NY5PC","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"TIPU6ITY","created_at":"2026-07-05T08:07:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TIPU6ITY5L5NY5PCMGOQAIPVEK","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T13:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"423079aa5377ce6f54a7722df3c8ca9db6fda4002dc4c0a70b884f21d0fa6096","abstract_canon_sha256":"4fc1aa1ef59656bb7a86c8028cc88522cffe0ae0b9670033193b62e1546ffeca"},"schema_version":"1.0"},"canonical_sha256":"9a1f4f2278eafadc75e2619d0021f522872ee78521e2c64ece2926e1193b4c58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:43.506668Z","signature_b64":"LOGiNVAuOE1pxrkB+b4+ApwybE9h4IfPRYLmtEk1ABEXyNsGYJ1sdo4ESBplKg44PSBUK5wnQV0kcEUs7OEyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a1f4f2278eafadc75e2619d0021f522872ee78521e2c64ece2926e1193b4c58","last_reissued_at":"2026-07-05T08:07:43.506249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:43.506249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09002","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:07:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hyMuCjjz/0b2fc3nE70sGAAkflimNic7PMXiNGuPRGCik2FXDvcE84LbfBwGxVCETVzvKVN1Bfb4C9irF6CVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:52:29.500371Z"},"content_sha256":"38ed3edab2555ac713ed8ecb1ff974ccf1a2c90f7ac0fd594cbe3deb7c699fa6","schema_version":"1.0","event_id":"sha256:38ed3edab2555ac713ed8ecb1ff974ccf1a2c90f7ac0fd594cbe3deb7c699fa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TIPU6ITY5L5NY5PCMGOQAIPVEK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WikiSplit++: Easy Data Refinement for Split and Rephrase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Katsuki Chousa, Koichi Takeda, Makoto Morishita, Ryohei Sasano, Tsutomu Hirao","submitted_at":"2024-04-13T13:07:32Z","abstract_excerpt":"The task of Split and Rephrase, which splits a complex sentence into multiple simple sentences with the same meaning, improves readability and enhances the performance of downstream tasks in natural language processing (NLP). However, while Split and Rephrase can be improved using a text-to-text generation approach that applies encoder-decoder models fine-tuned with a large-scale dataset, it still suffers from hallucinations and under-splitting. To address these issues, this paper presents a simple and strong data refinement approach. Here, we create WikiSplit++ by removing instances in WikiSp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09002","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/2404.09002/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":"2026-07-05T08:07:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UZps330+pSqgZYyMy1FwaxeVpaG6FSlLCWBxCfhOzNnO6tIpQ8TeDMLm0jJONF2VFKWxcxYhtb8yUtKUpTaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:52:29.500739Z"},"content_sha256":"1c8a5ea6ae7fd012abc486138d33964c7c8adf4506ca0f12f2b20c0bbced630f","schema_version":"1.0","event_id":"sha256:1c8a5ea6ae7fd012abc486138d33964c7c8adf4506ca0f12f2b20c0bbced630f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/bundle.json","state_url":"https://pith.science/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/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":"2026-07-09T03:52:29Z","links":{"resolver":"https://pith.science/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK","bundle":"https://pith.science/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/bundle.json","state":"https://pith.science/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TIPU6ITY5L5NY5PCMGOQAIPVEK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TIPU6ITY5L5NY5PCMGOQAIPVEK","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":"4fc1aa1ef59656bb7a86c8028cc88522cffe0ae0b9670033193b62e1546ffeca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T13:07:32Z","title_canon_sha256":"423079aa5377ce6f54a7722df3c8ca9db6fda4002dc4c0a70b884f21d0fa6096"},"schema_version":"1.0","source":{"id":"2404.09002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09002","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09002v1","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09002","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"TIPU6ITY5L5N","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"TIPU6ITY5L5NY5PC","created_at":"2026-07-05T08:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"TIPU6ITY","created_at":"2026-07-05T08:07:43Z"}],"graph_snapshots":[{"event_id":"sha256:1c8a5ea6ae7fd012abc486138d33964c7c8adf4506ca0f12f2b20c0bbced630f","target":"graph","created_at":"2026-07-05T08:07:43Z","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/2404.09002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of Split and Rephrase, which splits a complex sentence into multiple simple sentences with the same meaning, improves readability and enhances the performance of downstream tasks in natural language processing (NLP). However, while Split and Rephrase can be improved using a text-to-text generation approach that applies encoder-decoder models fine-tuned with a large-scale dataset, it still suffers from hallucinations and under-splitting. To address these issues, this paper presents a simple and strong data refinement approach. Here, we create WikiSplit++ by removing instances in WikiSp","authors_text":"Hayato Tsukagoshi, Katsuki Chousa, Koichi Takeda, Makoto Morishita, Ryohei Sasano, Tsutomu Hirao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T13:07:32Z","title":"WikiSplit++: Easy Data Refinement for Split and Rephrase"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09002","kind":"arxiv","version":1},"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":"sha256:38ed3edab2555ac713ed8ecb1ff974ccf1a2c90f7ac0fd594cbe3deb7c699fa6","target":"record","created_at":"2026-07-05T08:07:43Z","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":"4fc1aa1ef59656bb7a86c8028cc88522cffe0ae0b9670033193b62e1546ffeca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T13:07:32Z","title_canon_sha256":"423079aa5377ce6f54a7722df3c8ca9db6fda4002dc4c0a70b884f21d0fa6096"},"schema_version":"1.0","source":{"id":"2404.09002","kind":"arxiv","version":1}},"canonical_sha256":"9a1f4f2278eafadc75e2619d0021f522872ee78521e2c64ece2926e1193b4c58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a1f4f2278eafadc75e2619d0021f522872ee78521e2c64ece2926e1193b4c58","first_computed_at":"2026-07-05T08:07:43.506249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:43.506249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LOGiNVAuOE1pxrkB+b4+ApwybE9h4IfPRYLmtEk1ABEXyNsGYJ1sdo4ESBplKg44PSBUK5wnQV0kcEUs7OEyBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:43.506668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38ed3edab2555ac713ed8ecb1ff974ccf1a2c90f7ac0fd594cbe3deb7c699fa6","sha256:1c8a5ea6ae7fd012abc486138d33964c7c8adf4506ca0f12f2b20c0bbced630f"],"state_sha256":"20534978406ebca955a4f95a0179675c74b2a95e60033bd8784654c50cff5d45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKrlqczKeSL0o+xIyhjjNPcCQTXn8ql3vV0VQDcxAX32HZUdeLGf2DoF4FqqH66TNYtHpvTuodX4dQKStI/HBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:52:29.502677Z","bundle_sha256":"95062ce99db0bfd0e6e6146ae748599c1f9f8a93aa4cff94658119d75f1c8935"}}