{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KVR446R5RI76WHKRW6AANLCEUC","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":"690e4befca806fbd2019b61174cd16f829052c2b408dde8a17a11aea06628ea3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2025-06-30T13:57:11Z","title_canon_sha256":"30482829d20150f195fd1331b0fd1bb194a48fefa1dde94527d33b871205d99f"},"schema_version":"1.0","source":{"id":"2506.23862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23862","created_at":"2026-07-05T11:29:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23862v1","created_at":"2026-07-05T11:29:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23862","created_at":"2026-07-05T11:29:29Z"},{"alias_kind":"pith_short_12","alias_value":"KVR446R5RI76","created_at":"2026-07-05T11:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"KVR446R5RI76WHKR","created_at":"2026-07-05T11:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"KVR446R5","created_at":"2026-07-05T11:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:39850cb7c3cc2174f79eb9dbca3f7d0d12fe0693cd42309820df689cea545090","target":"graph","created_at":"2026-07-05T11:29:29Z","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/2506.23862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to reintroduce uncertainty, incorporate auxiliary information, and facilitate interpretability. For example, in the two-sample test, we compare the log-probability of strings under contexts from its own versus the other group. We show on synthetic data that the method's t-statistics exhibit the expected null behaviour while maintaining power and, through a replic","authors_text":"Marc Ratkovic","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2025-06-30T13:57:11Z","title":"Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23862","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:f32947e67e19de383757b3eaf6b5122093582db113172073d5c1d94acd694d16","target":"record","created_at":"2026-07-05T11:29:29Z","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":"690e4befca806fbd2019b61174cd16f829052c2b408dde8a17a11aea06628ea3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2025-06-30T13:57:11Z","title_canon_sha256":"30482829d20150f195fd1331b0fd1bb194a48fefa1dde94527d33b871205d99f"},"schema_version":"1.0","source":{"id":"2506.23862","kind":"arxiv","version":1}},"canonical_sha256":"5563ce7a3d8a3feb1d51b78006ac44a0a0eebc6544004d90c2e1507f66981bb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5563ce7a3d8a3feb1d51b78006ac44a0a0eebc6544004d90c2e1507f66981bb2","first_computed_at":"2026-07-05T11:29:29.178437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:29.178437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jbIlJkgXAswaMhPEGjCGcsaqSVewfmuURkhdEA2kA6IsaSOHhQL3PLIqFSIQUhRU3mHZJ8SanthUkN6HUfMMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:29.178901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f32947e67e19de383757b3eaf6b5122093582db113172073d5c1d94acd694d16","sha256:39850cb7c3cc2174f79eb9dbca3f7d0d12fe0693cd42309820df689cea545090"],"state_sha256":"7e78450391d68ca93fc9fbc80c75277cddb81adedb3157a19377109fe6c09d96"}