{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EKBT5UKVKAKWK6UUN2LFX2YLFC","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":"56ed6bb7e34fbf5209b2f1b9042a9d0388b818f46804883988c07d913df6e245","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-11T17:41:09Z","title_canon_sha256":"29062a651d28f551d05f35bc6428a5b6aff8ef0b1d66de6ae7637ccd83b1dbc8"},"schema_version":"1.0","source":{"id":"2606.13629","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13629","created_at":"2026-06-12T01:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13629v1","created_at":"2026-06-12T01:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13629","created_at":"2026-06-12T01:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"EKBT5UKVKAKW","created_at":"2026-06-12T01:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"EKBT5UKVKAKWK6UU","created_at":"2026-06-12T01:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"EKBT5UKV","created_at":"2026-06-12T01:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:9bb3fac150b35a4d262f0a02cef65ed7b88114d305f5c33280cc2626bdd2cb4f","target":"graph","created_at":"2026-06-12T01:10:15Z","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/2606.13629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social scientists are arguing for the use of LLM-generated \"silicon samples\" in pilot studies; AI evaluations increasingly rely on \"LLM-as-a-judge\" outputs; and proteomics research is accelerated by generative models that produce synthetic protein structures. These developments raise an intriguing possibility: synthetic data may help researchers ask more questions, run more studies, and accelerate discovery. But they also raise a fundamental concern: synthetic data can be biased, noisy, ","authors_text":"Lezhi Tan, Tijana Zrnic","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-11T17:41:09Z","title":"Valid Inference with Synthetic Data via Task Exchangeability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13629","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:ecf6cf1b6ebf6799705abd545c62b9aa785f1329029d4797711c14ffc8946ca2","target":"record","created_at":"2026-06-12T01:10:15Z","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":"56ed6bb7e34fbf5209b2f1b9042a9d0388b818f46804883988c07d913df6e245","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-11T17:41:09Z","title_canon_sha256":"29062a651d28f551d05f35bc6428a5b6aff8ef0b1d66de6ae7637ccd83b1dbc8"},"schema_version":"1.0","source":{"id":"2606.13629","kind":"arxiv","version":1}},"canonical_sha256":"22833ed1555015657a946e965beb0b28a04a9fc91d01a20b697ac4ba97a40ee0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22833ed1555015657a946e965beb0b28a04a9fc91d01a20b697ac4ba97a40ee0","first_computed_at":"2026-06-12T01:10:15.960471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:15.960471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5pxOGwaAdYL3lnVQzGDtmRf0HaDCPX/qgHMGgPTLatsTBUMGLP9QCtw0mHUneJMk5zeu4Z4g3xhggPj13OFqBg==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:15.961256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13629","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecf6cf1b6ebf6799705abd545c62b9aa785f1329029d4797711c14ffc8946ca2","sha256:9bb3fac150b35a4d262f0a02cef65ed7b88114d305f5c33280cc2626bdd2cb4f"],"state_sha256":"fa4c4e25d09cac07a0e3dc9656b4794b7dcd98ad90157f0dc7ce39e5918873ae"}