{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5SRO4UDHYIPLJJCZB2B25LYJI4","short_pith_number":"pith:5SRO4UDH","canonical_record":{"source":{"id":"2404.07503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"e2fe1fc81785db559018499dc5c0bb22d3b66fc8fd582ecd9a2d46385cccb50d","abstract_canon_sha256":"5196484e3fa7063178f443fd4440d1e596afd531bf32aac4a3030e979f4e573c"},"schema_version":"1.0"},"canonical_sha256":"eca2ee5067c21eb4a4590e83aeaf09472e9b4dfa948ef02190e0f00b4f455484","source":{"kind":"arxiv","id":"2404.07503","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07503","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07503v2","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07503","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_12","alias_value":"5SRO4UDHYIPL","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_16","alias_value":"5SRO4UDHYIPLJJCZ","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_8","alias_value":"5SRO4UDH","created_at":"2026-07-05T08:54:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5SRO4UDHYIPLJJCZB2B25LYJI4","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"e2fe1fc81785db559018499dc5c0bb22d3b66fc8fd582ecd9a2d46385cccb50d","abstract_canon_sha256":"5196484e3fa7063178f443fd4440d1e596afd531bf32aac4a3030e979f4e573c"},"schema_version":"1.0"},"canonical_sha256":"eca2ee5067c21eb4a4590e83aeaf09472e9b4dfa948ef02190e0f00b4f455484","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:10.019290Z","signature_b64":"L8N/nroYX6TEUNwrWLQlatKkrIEgafY30ETgGqomgXpNnm2x8woPb61PBMCztB/r42ERhxLcM5UFmI2GebBWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eca2ee5067c21eb4a4590e83aeaf09472e9b4dfa948ef02190e0f00b4f455484","last_reissued_at":"2026-07-05T08:54:10.018866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:10.018866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07503","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":"2026-07-05T08:54:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HTJ7cAfu5Th0kSj7fEUjKRVPMTJ1osqb4IwkvHVhG1ZqNjeqKBbYlPjR7Xu9cNtMNYHxu19P6nvz5Vj/AiTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:38:50.181596Z"},"content_sha256":"7af01cbb125dcbac17934f23fd86f5d97cc5418982727e5edc912f81300b9a0a","schema_version":"1.0","event_id":"sha256:7af01cbb125dcbac17934f23fd86f5d97cc5418982727e5edc912f81300b9a0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5SRO4UDHYIPLJJCZB2B25LYJI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Best Practices and Lessons Learned on Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew M. Dai, Chenglei Si, Daiyi Peng, Denny Zhou, Diyi Yang, Fangyu Liu, Jerry Wei, Jinmeng Rao, Ruibo Liu, Steven Zheng, Yanzhe Zhang","submitted_at":"2024-04-11T06:34:17Z","abstract_excerpt":"The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns. This paper provides an overview of synthetic data research, discussing its applications, challenges, and future directions. We present empirical evidence from prior art to demonstrate its effectiveness and highlight the importance of ensuring its factuality, fidelity, and unbiasedness. We emphasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07503","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/2404.07503/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":"2026-07-05T08:54:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4V5DeFcmxe4g2DIwac4m0Q3AnuCeoDvoaTHWJ19HjEBJt415GARpPasJjYTZO+9xgkhK2iYLoOb9p37CQEDnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:38:50.182250Z"},"content_sha256":"3796637264fa04271718089c3346bb1ea7dcbee5f99018c50c9af56e86f08021","schema_version":"1.0","event_id":"sha256:3796637264fa04271718089c3346bb1ea7dcbee5f99018c50c9af56e86f08021"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/bundle.json","state_url":"https://pith.science/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/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":"2026-08-10T02:38:50Z","links":{"resolver":"https://pith.science/pith/5SRO4UDHYIPLJJCZB2B25LYJI4","bundle":"https://pith.science/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/bundle.json","state":"https://pith.science/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SRO4UDHYIPLJJCZB2B25LYJI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5SRO4UDHYIPLJJCZB2B25LYJI4","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":"5196484e3fa7063178f443fd4440d1e596afd531bf32aac4a3030e979f4e573c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:34:17Z","title_canon_sha256":"e2fe1fc81785db559018499dc5c0bb22d3b66fc8fd582ecd9a2d46385cccb50d"},"schema_version":"1.0","source":{"id":"2404.07503","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07503","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07503v2","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07503","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_12","alias_value":"5SRO4UDHYIPL","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_16","alias_value":"5SRO4UDHYIPLJJCZ","created_at":"2026-07-05T08:54:10Z"},{"alias_kind":"pith_short_8","alias_value":"5SRO4UDH","created_at":"2026-07-05T08:54:10Z"}],"graph_snapshots":[{"event_id":"sha256:3796637264fa04271718089c3346bb1ea7dcbee5f99018c50c9af56e86f08021","target":"graph","created_at":"2026-07-05T08:54:10Z","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/2404.07503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns. This paper provides an overview of synthetic data research, discussing its applications, challenges, and future directions. We present empirical evidence from prior art to demonstrate its effectiveness and highlight the importance of ensuring its factuality, fidelity, and unbiasedness. We emphasi","authors_text":"Andrew M. Dai, Chenglei Si, Daiyi Peng, Denny Zhou, Diyi Yang, Fangyu Liu, Jerry Wei, Jinmeng Rao, Ruibo Liu, Steven Zheng, Yanzhe Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:34:17Z","title":"Best Practices and Lessons Learned on Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07503","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":"sha256:7af01cbb125dcbac17934f23fd86f5d97cc5418982727e5edc912f81300b9a0a","target":"record","created_at":"2026-07-05T08:54:10Z","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":"5196484e3fa7063178f443fd4440d1e596afd531bf32aac4a3030e979f4e573c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:34:17Z","title_canon_sha256":"e2fe1fc81785db559018499dc5c0bb22d3b66fc8fd582ecd9a2d46385cccb50d"},"schema_version":"1.0","source":{"id":"2404.07503","kind":"arxiv","version":2}},"canonical_sha256":"eca2ee5067c21eb4a4590e83aeaf09472e9b4dfa948ef02190e0f00b4f455484","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eca2ee5067c21eb4a4590e83aeaf09472e9b4dfa948ef02190e0f00b4f455484","first_computed_at":"2026-07-05T08:54:10.018866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:10.018866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L8N/nroYX6TEUNwrWLQlatKkrIEgafY30ETgGqomgXpNnm2x8woPb61PBMCztB/r42ERhxLcM5UFmI2GebBWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:10.019290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07503","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7af01cbb125dcbac17934f23fd86f5d97cc5418982727e5edc912f81300b9a0a","sha256:3796637264fa04271718089c3346bb1ea7dcbee5f99018c50c9af56e86f08021"],"state_sha256":"b469622647091ad92d0161b8f621b2031af67e8051f33176b1823d81a7cf925c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwxVpMopC0/ieLXMF2uM5aHtNeoSOMIeDjeF9snig+MOjdhbS7ULbcd7/4cQwNMOjYW7Usm/4uSFWB23n2EhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:38:50.187098Z","bundle_sha256":"8842d1b59acbb06a56156cd997293b66d217464974d60129ce886c2615af8bf3"}}