{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EKBT5UKVKAKWK6UUN2LFX2YLFC","short_pith_number":"pith:EKBT5UKV","schema_version":"1.0","canonical_sha256":"22833ed1555015657a946e965beb0b28a04a9fc91d01a20b697ac4ba97a40ee0","source":{"kind":"arxiv","id":"2606.13629","version":1},"attestation_state":"computed","paper":{"title":"Valid Inference with Synthetic Data via Task Exchangeability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Lezhi Tan, Tijana Zrnic","submitted_at":"2026-06-11T17:41:09Z","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, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.13629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-11T17:41:09Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"29062a651d28f551d05f35bc6428a5b6aff8ef0b1d66de6ae7637ccd83b1dbc8","abstract_canon_sha256":"56ed6bb7e34fbf5209b2f1b9042a9d0388b818f46804883988c07d913df6e245"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:15.961256Z","signature_b64":"5pxOGwaAdYL3lnVQzGDtmRf0HaDCPX/qgHMGgPTLatsTBUMGLP9QCtw0mHUneJMk5zeu4Z4g3xhggPj13OFqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22833ed1555015657a946e965beb0b28a04a9fc91d01a20b697ac4ba97a40ee0","last_reissued_at":"2026-06-12T01:10:15.960471Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:15.960471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Valid Inference with Synthetic Data via Task Exchangeability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Lezhi Tan, Tijana Zrnic","submitted_at":"2026-06-11T17:41:09Z","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, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13629","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/2606.13629/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.13629","created_at":"2026-06-12T01:10:15.960603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13629v1","created_at":"2026-06-12T01:10:15.960603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13629","created_at":"2026-06-12T01:10:15.960603+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKBT5UKVKAKW","created_at":"2026-06-12T01:10:15.960603+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKBT5UKVKAKWK6UU","created_at":"2026-06-12T01:10:15.960603+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKBT5UKV","created_at":"2026-06-12T01:10:15.960603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC","json":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC.json","graph_json":"https://pith.science/api/pith-number/EKBT5UKVKAKWK6UUN2LFX2YLFC/graph.json","events_json":"https://pith.science/api/pith-number/EKBT5UKVKAKWK6UUN2LFX2YLFC/events.json","paper":"https://pith.science/paper/EKBT5UKV"},"agent_actions":{"view_html":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC","download_json":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC.json","view_paper":"https://pith.science/paper/EKBT5UKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13629&json=true","fetch_graph":"https://pith.science/api/pith-number/EKBT5UKVKAKWK6UUN2LFX2YLFC/graph.json","fetch_events":"https://pith.science/api/pith-number/EKBT5UKVKAKWK6UUN2LFX2YLFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC/action/storage_attestation","attest_author":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC/action/author_attestation","sign_citation":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC/action/citation_signature","submit_replication":"https://pith.science/pith/EKBT5UKVKAKWK6UUN2LFX2YLFC/action/replication_record"}},"created_at":"2026-06-12T01:10:15.960603+00:00","updated_at":"2026-06-12T01:10:15.960603+00:00"}