{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7F2QMH3ZQF53U7VRERJGRXE7ZH","short_pith_number":"pith:7F2QMH3Z","canonical_record":{"source":{"id":"2407.00322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T05:40:17Z","cross_cats_sorted":[],"title_canon_sha256":"f462d63e41536a8f64b66a296ead68a94b10303f9528c6bf875a5c0ab0198c93","abstract_canon_sha256":"3a8f241c85f6ef188510c297fa609970156ea94ce76d52752adca7d9cf381582"},"schema_version":"1.0"},"canonical_sha256":"f975061f79817bba7eb1245268dc9fc9c19c044c50eb2063274aa569224d96ff","source":{"kind":"arxiv","id":"2407.00322","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00322","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00322v1","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00322","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_12","alias_value":"7F2QMH3ZQF53","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_16","alias_value":"7F2QMH3ZQF53U7VR","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_8","alias_value":"7F2QMH3Z","created_at":"2026-07-05T08:38:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7F2QMH3ZQF53U7VRERJGRXE7ZH","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T05:40:17Z","cross_cats_sorted":[],"title_canon_sha256":"f462d63e41536a8f64b66a296ead68a94b10303f9528c6bf875a5c0ab0198c93","abstract_canon_sha256":"3a8f241c85f6ef188510c297fa609970156ea94ce76d52752adca7d9cf381582"},"schema_version":"1.0"},"canonical_sha256":"f975061f79817bba7eb1245268dc9fc9c19c044c50eb2063274aa569224d96ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:18.082462Z","signature_b64":"/HN2ZnUabwZVTc/XkpRftG7V1VSkYEtLruinhXGcDBosZeNRk/dcVZLl8Bo5WVm/A2uu78+2TNOJga8eo47MCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f975061f79817bba7eb1245268dc9fc9c19c044c50eb2063274aa569224d96ff","last_reissued_at":"2026-07-05T08:38:18.081975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:18.081975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00322","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":"2026-07-05T08:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IDb9FDpawX7VhMg6E7RFc8RyUfRO76e0I/Q7IX0KghotCG2Vvtvr2F37aa3Sy13QOcUCmrKpYyBbUqqBMzCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:37.160800Z"},"content_sha256":"d45013e8727b28a4ba98a4c2184efb96ab9ab90e0de892c5a15fd3dc6a2ed69c","schema_version":"1.0","event_id":"sha256:d45013e8727b28a4ba98a4c2184efb96ab9ab90e0de892c5a15fd3dc6a2ed69c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7F2QMH3ZQF53U7VRERJGRXE7ZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guang Xu, Ming Ren, Zhenhua Wang","submitted_at":"2024-06-29T05:40:17Z","abstract_excerpt":"With the ascent of large language models (LLM), natural language processing has witnessed enhancements, such as LLM-based data augmentation. Nonetheless, prior research harbors two primary concerns: firstly, a lack of contemplation regarding whether the natural language generated by LLM (LLMNL) truly aligns with human natural language (HNL), a critical foundational question; secondly, an oversight that augmented data is randomly generated by LLM, implying that not all data may possess equal training value, that could impede the performance of classifiers. To address these challenges, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00322","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/2407.00322/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":"2026-07-05T08:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IitvVQ3tTaWev6u03z+v0rbO4yIWHVum9PXwgdtySu42EX1imeHJpCNcIeeFmxjILbHZleOa/GjOiCWwzarHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:37.161309Z"},"content_sha256":"b09643eee367c085a7e37917e63b61e0072d25ade35bf3d21a30dd404d4cb349","schema_version":"1.0","event_id":"sha256:b09643eee367c085a7e37917e63b61e0072d25ade35bf3d21a30dd404d4cb349"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/bundle.json","state_url":"https://pith.science/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/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":"2026-08-09T07:50:37Z","links":{"resolver":"https://pith.science/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH","bundle":"https://pith.science/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/bundle.json","state":"https://pith.science/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7F2QMH3ZQF53U7VRERJGRXE7ZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7F2QMH3ZQF53U7VRERJGRXE7ZH","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":"3a8f241c85f6ef188510c297fa609970156ea94ce76d52752adca7d9cf381582","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T05:40:17Z","title_canon_sha256":"f462d63e41536a8f64b66a296ead68a94b10303f9528c6bf875a5c0ab0198c93"},"schema_version":"1.0","source":{"id":"2407.00322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00322","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00322v1","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00322","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_12","alias_value":"7F2QMH3ZQF53","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_16","alias_value":"7F2QMH3ZQF53U7VR","created_at":"2026-07-05T08:38:18Z"},{"alias_kind":"pith_short_8","alias_value":"7F2QMH3Z","created_at":"2026-07-05T08:38:18Z"}],"graph_snapshots":[{"event_id":"sha256:b09643eee367c085a7e37917e63b61e0072d25ade35bf3d21a30dd404d4cb349","target":"graph","created_at":"2026-07-05T08:38:18Z","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/2407.00322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the ascent of large language models (LLM), natural language processing has witnessed enhancements, such as LLM-based data augmentation. Nonetheless, prior research harbors two primary concerns: firstly, a lack of contemplation regarding whether the natural language generated by LLM (LLMNL) truly aligns with human natural language (HNL), a critical foundational question; secondly, an oversight that augmented data is randomly generated by LLM, implying that not all data may possess equal training value, that could impede the performance of classifiers. To address these challenges, we introd","authors_text":"Guang Xu, Ming Ren, Zhenhua Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T05:40:17Z","title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00322","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:d45013e8727b28a4ba98a4c2184efb96ab9ab90e0de892c5a15fd3dc6a2ed69c","target":"record","created_at":"2026-07-05T08:38:18Z","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":"3a8f241c85f6ef188510c297fa609970156ea94ce76d52752adca7d9cf381582","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T05:40:17Z","title_canon_sha256":"f462d63e41536a8f64b66a296ead68a94b10303f9528c6bf875a5c0ab0198c93"},"schema_version":"1.0","source":{"id":"2407.00322","kind":"arxiv","version":1}},"canonical_sha256":"f975061f79817bba7eb1245268dc9fc9c19c044c50eb2063274aa569224d96ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f975061f79817bba7eb1245268dc9fc9c19c044c50eb2063274aa569224d96ff","first_computed_at":"2026-07-05T08:38:18.081975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:18.081975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HN2ZnUabwZVTc/XkpRftG7V1VSkYEtLruinhXGcDBosZeNRk/dcVZLl8Bo5WVm/A2uu78+2TNOJga8eo47MCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:18.082462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d45013e8727b28a4ba98a4c2184efb96ab9ab90e0de892c5a15fd3dc6a2ed69c","sha256:b09643eee367c085a7e37917e63b61e0072d25ade35bf3d21a30dd404d4cb349"],"state_sha256":"cf8ac5ec0da1aca85c43f57279598694da3900de73c7b8e64f2d2693bb405308"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J1yDRPXpcOMm5FpB/d+AZ/cqXxyhQjsSmQyCTudleevQ7JQnxtuxXKfTiZ/utXuMigh/LYp/Xb9F0QgUcYYCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:50:37.166964Z","bundle_sha256":"475ac4ea1c8353b829288963a03a870b40e8d74427921e5b5aa460d325eca632"}}