{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PHCMAHGK4PPTIWORWOWSILMP3N","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":"950978af0406cdb502c12a2f669896cebc28e34db8fd210a7c8d81994f6f2469","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-23T17:59:09Z","title_canon_sha256":"0671cf794722ddd2af295d4faa1e5cadac2a683b95319706c97aef72a404e3d5"},"schema_version":"1.0","source":{"id":"2306.13651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13651","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13651v2","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13651","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"PHCMAHGK4PPT","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"PHCMAHGK4PPTIWOR","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"PHCMAHGK","created_at":"2026-07-05T06:26:03Z"}],"graph_snapshots":[{"event_id":"sha256:c7493b75ea2ceaf4cb2d0dbdb6d0b221bef2a8b0a11c3e6576c27b34f48da721","target":"graph","created_at":"2026-07-05T06:26:03Z","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/2306.13651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that the model will not respond to client requests with profanity. Current evaluations approach this problem using small, domain-specific datasets with human-curated labels. These evaluation sets are often sampled from a narrow and simplified distribution, and data sources can unknowingly be leaked into the training set which can lead to misleading evaluations. To","authors_text":"Aniruddha Saha, John Kirchenbauer, Jonas Geiping, Khalid Saifullah, Manli Shu, Micah Goldblum, Neel Jain, Tom Goldstein, Yuxin Wen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-23T17:59:09Z","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13651","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:edba5ef49f97a0a4022878e72b6e78cca2e8e873eb3632a5a17a415d41dfd85e","target":"record","created_at":"2026-07-05T06:26:03Z","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":"950978af0406cdb502c12a2f669896cebc28e34db8fd210a7c8d81994f6f2469","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-23T17:59:09Z","title_canon_sha256":"0671cf794722ddd2af295d4faa1e5cadac2a683b95319706c97aef72a404e3d5"},"schema_version":"1.0","source":{"id":"2306.13651","kind":"arxiv","version":2}},"canonical_sha256":"79c4c01ccae3df3459d1b3ad242d8fdb7daca57d4fb0d79c824ac4bb22a1f878","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79c4c01ccae3df3459d1b3ad242d8fdb7daca57d4fb0d79c824ac4bb22a1f878","first_computed_at":"2026-07-05T06:26:03.381419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:03.381419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/OG17hZR5smzlbdWZdg+XqmBcTka6PrCAmysmog9Dkr/3baRXXyuWcjNpNwQ4zb3i/dWlpmvZYvkTlC6Mc1yBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:03.381813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edba5ef49f97a0a4022878e72b6e78cca2e8e873eb3632a5a17a415d41dfd85e","sha256:c7493b75ea2ceaf4cb2d0dbdb6d0b221bef2a8b0a11c3e6576c27b34f48da721"],"state_sha256":"913dada51aa6d24ca4dbb47535ddd08edb8917fe5799c81bbe7392a579e18792"}