{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W5IJQHMB3VFHQMXDB6X4Y4HMQH","short_pith_number":"pith:W5IJQHMB","canonical_record":{"source":{"id":"2406.15126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"3bca951607f960bc01f36a578530a7a148a7e140406fd3dcfb35e075134419d3","abstract_canon_sha256":"5e681137d605bae5dffde63508ef8643c40676f3d50cbf205aeef5b9a283d8da"},"schema_version":"1.0"},"canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","source":{"kind":"arxiv","id":"2406.15126","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15126","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15126v1","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15126","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"W5IJQHMB3VFH","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"W5IJQHMB3VFHQMXD","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"W5IJQHMB","created_at":"2026-07-05T08:35:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W5IJQHMB3VFHQMXDB6X4Y4HMQH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"3bca951607f960bc01f36a578530a7a148a7e140406fd3dcfb35e075134419d3","abstract_canon_sha256":"5e681137d605bae5dffde63508ef8643c40676f3d50cbf205aeef5b9a283d8da"},"schema_version":"1.0"},"canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:14.417996Z","signature_b64":"BHXFmyXayL1Dc+QAnfT4JxeAyEezbnzT2KBFkp+vk2xcMA61fwR02sRUjHhzeJmvbwizmg1ufPpSmHuR0XL6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","last_reissued_at":"2026-07-05T08:35:14.417587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:14.417587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15126","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":"2026-07-05T08:35:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlUtWE7T4jkTe6OuiI+e+6YlDYgqkFuRdu4rlIrGm8OUQpX1qwn3wyRSJfD1FzvJioCF/mUbQTHDu/QGS/5+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:59:28.506502Z"},"content_sha256":"04d66c0986b53b0cbcc116a3c6e787c01b85e130e3828f7b0829d40f9f478fff","schema_version":"1.0","event_id":"sha256:04d66c0986b53b0cbcc116a3c6e787c01b85e130e3828f7b0829d40f9f478fff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W5IJQHMB3VFHQMXDB6X4Y4HMQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gang Chen, Haobo Wang, Junbo Zhao, Lin Long, Rui Wang, Ruixuan Xiao, Xiao Ding","submitted_at":"2024-06-14T07:47:09Z","abstract_excerpt":"Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of real-world data with synthetic data generation. However, current investigations into this field lack a unified framework and mostly stay on the surface. Therefore, this paper provides an organization of relevant studies based on a generic workflow of synthetic data generation. By doing so, we highlight the gaps within existing research and outline prospective av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15126","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/2406.15126/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":"2026-07-05T08:35:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csQX6G+Wirm0wYl3ZVtEmKDjrN/T22aL76W0gCHvbGEwEfTpdmh70PPFAw1wfID3xMrO6HN2Cn1o1QqFXbtIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:59:28.507012Z"},"content_sha256":"678fc96d68ee819d27eaec33dc08c75429c5aa4bb0d8be49154baf22e1e0129b","schema_version":"1.0","event_id":"sha256:678fc96d68ee819d27eaec33dc08c75429c5aa4bb0d8be49154baf22e1e0129b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/bundle.json","state_url":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/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":"2026-08-09T07:59:28Z","links":{"resolver":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH","bundle":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/bundle.json","state":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W5IJQHMB3VFHQMXDB6X4Y4HMQH","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":"5e681137d605bae5dffde63508ef8643c40676f3d50cbf205aeef5b9a283d8da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","title_canon_sha256":"3bca951607f960bc01f36a578530a7a148a7e140406fd3dcfb35e075134419d3"},"schema_version":"1.0","source":{"id":"2406.15126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15126","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15126v1","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15126","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"W5IJQHMB3VFH","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"W5IJQHMB3VFHQMXD","created_at":"2026-07-05T08:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"W5IJQHMB","created_at":"2026-07-05T08:35:14Z"}],"graph_snapshots":[{"event_id":"sha256:678fc96d68ee819d27eaec33dc08c75429c5aa4bb0d8be49154baf22e1e0129b","target":"graph","created_at":"2026-07-05T08:35:14Z","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/2406.15126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of real-world data with synthetic data generation. However, current investigations into this field lack a unified framework and mostly stay on the surface. Therefore, this paper provides an organization of relevant studies based on a generic workflow of synthetic data generation. By doing so, we highlight the gaps within existing research and outline prospective av","authors_text":"Gang Chen, Haobo Wang, Junbo Zhao, Lin Long, Rui Wang, Ruixuan Xiao, Xiao Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15126","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":"sha256:04d66c0986b53b0cbcc116a3c6e787c01b85e130e3828f7b0829d40f9f478fff","target":"record","created_at":"2026-07-05T08:35:14Z","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":"5e681137d605bae5dffde63508ef8643c40676f3d50cbf205aeef5b9a283d8da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","title_canon_sha256":"3bca951607f960bc01f36a578530a7a148a7e140406fd3dcfb35e075134419d3"},"schema_version":"1.0","source":{"id":"2406.15126","kind":"arxiv","version":1}},"canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","first_computed_at":"2026-07-05T08:35:14.417587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:14.417587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHXFmyXayL1Dc+QAnfT4JxeAyEezbnzT2KBFkp+vk2xcMA61fwR02sRUjHhzeJmvbwizmg1ufPpSmHuR0XL6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:14.417996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04d66c0986b53b0cbcc116a3c6e787c01b85e130e3828f7b0829d40f9f478fff","sha256:678fc96d68ee819d27eaec33dc08c75429c5aa4bb0d8be49154baf22e1e0129b"],"state_sha256":"7c01821fb6f5b9f944de2b9f9357c7227e82447997d35605afc6a13b25c5b3b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZM6+3pHJs9tw1fyP6p9+9Rbun2l7WLd+0GTPJc00OyHgdjbWP7/lgJ1zWw0TBGje5nvlO4b3wYGKzP8fakn6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:59:28.510725Z","bundle_sha256":"5ce57affff3aef104b71aedd31b6dd0646680ee84214e6d5fcc80030824b5f72"}}