{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4DOD7SROJXYDPC6H7H2JHZ23CF","short_pith_number":"pith:4DOD7SRO","canonical_record":{"source":{"id":"2501.18493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-30T17:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"dd38d3b231d07642c5a4211fd47902aed2414d75db6decb06308cb722f737b6d","abstract_canon_sha256":"37a0bd98644f7cb7cb258d8b393dcc2d9e1df269114e47022d5255e6f16f2913"},"schema_version":"1.0"},"canonical_sha256":"e0dc3fca2e4df0378bc7f9f493e75b11497fe94b7f9acca78142c716c71eb1a4","source":{"kind":"arxiv","id":"2501.18493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18493","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18493v2","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18493","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"4DOD7SROJXYD","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"4DOD7SROJXYDPC6H","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"4DOD7SRO","created_at":"2026-07-05T11:01:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4DOD7SROJXYDPC6H7H2JHZ23CF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-30T17:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"dd38d3b231d07642c5a4211fd47902aed2414d75db6decb06308cb722f737b6d","abstract_canon_sha256":"37a0bd98644f7cb7cb258d8b393dcc2d9e1df269114e47022d5255e6f16f2913"},"schema_version":"1.0"},"canonical_sha256":"e0dc3fca2e4df0378bc7f9f493e75b11497fe94b7f9acca78142c716c71eb1a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:56.715764Z","signature_b64":"pdXumJjNQ2j4r1pK+gv3YdqVhIvL98nYRjDjDCUONIrTIh9rmT7xsKK/TAOlP8N7XmP2LNN+94Pe+ghKm/V9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0dc3fca2e4df0378bc7f9f493e75b11497fe94b7f9acca78142c716c71eb1a4","last_reissued_at":"2026-07-05T11:01:56.715191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:56.715191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18493","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":"2026-07-05T11:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9iCyS9C2RwxgmmhOcL9r2XaGAGnfXLI20gS8q66aOBp+HvUv0mABTu+OwHnfW7BJ+qmkL0n3Dq4MO3V9UQVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:14:39.555989Z"},"content_sha256":"46370479488b0bc20b066a21f81ffb94e4983593e0a2d4205fb9b7ca24d7292a","schema_version":"1.0","event_id":"sha256:46370479488b0bc20b066a21f81ffb94e4983593e0a2d4205fb9b7ca24d7292a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4DOD7SROJXYDPC6H7H2JHZ23CF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Examining the Expanding Role of Synthetic Data Throughout the AI Development Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alex Kessler, Jennifer Wortman Vaughan, Shivani Kapania, Stephanie Ballard","submitted_at":"2025-01-30T17:06:56Z","abstract_excerpt":"Alongside the growth of generative AI, we are witnessing a surge in the use of synthetic data across all stages of the AI development pipeline. It is now common practice for researchers and practitioners to use one large generative model (which we refer to as an auxiliary model) to generate synthetic data that is used to train or evaluate another, reconfiguring AI workflows and reshaping the very nature of data. While scholars have raised concerns over the risks of synthetic data, policy guidance and best practices for its responsible use have not kept up with these rapidly evolving industry t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18493","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/2501.18493/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":"2026-07-05T11:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WzDqBUI3wm7oTihftfvLWzfk31s0K/xW8TXAtIKMVYq0JOM94HqBx4Edngvreh97SeHRs5n6BHroy5GKzIrCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:14:39.556516Z"},"content_sha256":"29820fb4f4573c22b8cf081f9026e047c1f3be4ae7d2b4c36bae098cad5168a4","schema_version":"1.0","event_id":"sha256:29820fb4f4573c22b8cf081f9026e047c1f3be4ae7d2b4c36bae098cad5168a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/bundle.json","state_url":"https://pith.science/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/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":"2026-08-07T10:14:39Z","links":{"resolver":"https://pith.science/pith/4DOD7SROJXYDPC6H7H2JHZ23CF","bundle":"https://pith.science/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/bundle.json","state":"https://pith.science/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DOD7SROJXYDPC6H7H2JHZ23CF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4DOD7SROJXYDPC6H7H2JHZ23CF","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":"37a0bd98644f7cb7cb258d8b393dcc2d9e1df269114e47022d5255e6f16f2913","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-30T17:06:56Z","title_canon_sha256":"dd38d3b231d07642c5a4211fd47902aed2414d75db6decb06308cb722f737b6d"},"schema_version":"1.0","source":{"id":"2501.18493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18493","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18493v2","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18493","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"4DOD7SROJXYD","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"4DOD7SROJXYDPC6H","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"4DOD7SRO","created_at":"2026-07-05T11:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:29820fb4f4573c22b8cf081f9026e047c1f3be4ae7d2b4c36bae098cad5168a4","target":"graph","created_at":"2026-07-05T11:01:56Z","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/2501.18493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alongside the growth of generative AI, we are witnessing a surge in the use of synthetic data across all stages of the AI development pipeline. It is now common practice for researchers and practitioners to use one large generative model (which we refer to as an auxiliary model) to generate synthetic data that is used to train or evaluate another, reconfiguring AI workflows and reshaping the very nature of data. While scholars have raised concerns over the risks of synthetic data, policy guidance and best practices for its responsible use have not kept up with these rapidly evolving industry t","authors_text":"Alex Kessler, Jennifer Wortman Vaughan, Shivani Kapania, Stephanie Ballard","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-30T17:06:56Z","title":"Examining the Expanding Role of Synthetic Data Throughout the AI Development Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18493","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":"sha256:46370479488b0bc20b066a21f81ffb94e4983593e0a2d4205fb9b7ca24d7292a","target":"record","created_at":"2026-07-05T11:01:56Z","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":"37a0bd98644f7cb7cb258d8b393dcc2d9e1df269114e47022d5255e6f16f2913","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-30T17:06:56Z","title_canon_sha256":"dd38d3b231d07642c5a4211fd47902aed2414d75db6decb06308cb722f737b6d"},"schema_version":"1.0","source":{"id":"2501.18493","kind":"arxiv","version":2}},"canonical_sha256":"e0dc3fca2e4df0378bc7f9f493e75b11497fe94b7f9acca78142c716c71eb1a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0dc3fca2e4df0378bc7f9f493e75b11497fe94b7f9acca78142c716c71eb1a4","first_computed_at":"2026-07-05T11:01:56.715191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:56.715191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pdXumJjNQ2j4r1pK+gv3YdqVhIvL98nYRjDjDCUONIrTIh9rmT7xsKK/TAOlP8N7XmP2LNN+94Pe+ghKm/V9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:56.715764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46370479488b0bc20b066a21f81ffb94e4983593e0a2d4205fb9b7ca24d7292a","sha256:29820fb4f4573c22b8cf081f9026e047c1f3be4ae7d2b4c36bae098cad5168a4"],"state_sha256":"250d50c02551e0a89abf764eb1f58dc84b19e4978fd6d7a9dd40faa6ed844769"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQJY3ryKyK/iyk7irkyA4lYOj1HHBQyLIIecfH3dgqMfew8Kv4auL7P65KHyHKCjM0ju38pbGo6yQfkMuJ7gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:14:39.560985Z","bundle_sha256":"73e4d08f3fc57a09ac730debc86a82c421b066cec2f92b9d4a26a0bd151a9bfd"}}