{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKYXFAKT42C3OS3547IJO7NXIQ","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":"1009d9516f4ce2a860e5eef09206530749ab208a83e46e40ab359d6ef95feb41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T21:04:23Z","title_canon_sha256":"217cec6fa26dfab8d15be57e72885e6357ea165acccc676f473bd50b3eaec336"},"schema_version":"1.0","source":{"id":"2504.14738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14738","created_at":"2026-07-05T10:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14738v1","created_at":"2026-07-05T10:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14738","created_at":"2026-07-05T10:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"MKYXFAKT42C3","created_at":"2026-07-05T10:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"MKYXFAKT42C3OS35","created_at":"2026-07-05T10:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"MKYXFAKT","created_at":"2026-07-05T10:51:49Z"}],"graph_snapshots":[{"event_id":"sha256:b49e186faf68321e6aa1e4f05022c5b336f6aa631ff6f5bf2b49962d4b3fac36","target":"graph","created_at":"2026-07-05T10:51:49Z","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/2504.14738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in specialized production data processing pipelines across diverse domains -- such as finance, marketing, and e-commerce. However, when running them in production across many inputs, they often fail to follow instructions or meet developer expectations. To improve reliability in these applications, creating assertions or guardrails for LLM outputs to run alongside the pipelines is essential. Yet, determining the right set of assertions that capture developer requirements for a task is challenging. In this paper, we introduce PROMPTEVALS, a","authors_text":"Aditya Parameswaran, Harrison Chase, Reya Vir, Shreya Shankar, Will Fu-Hinthorn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T21:04:23Z","title":"PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14738","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":"sha256:199ba5cda6a509e19dba61f3d247ee903f13d3032e1fc660362186650acb7e75","target":"record","created_at":"2026-07-05T10:51:49Z","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":"1009d9516f4ce2a860e5eef09206530749ab208a83e46e40ab359d6ef95feb41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T21:04:23Z","title_canon_sha256":"217cec6fa26dfab8d15be57e72885e6357ea165acccc676f473bd50b3eaec336"},"schema_version":"1.0","source":{"id":"2504.14738","kind":"arxiv","version":1}},"canonical_sha256":"62b1728153e685b74b7de7d0977db744375879aede867ae89fb07be5a72c0b4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62b1728153e685b74b7de7d0977db744375879aede867ae89fb07be5a72c0b4a","first_computed_at":"2026-07-05T10:51:49.842952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:49.842952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQdKoAzJvecSKsqcPUxQGhLrC01iydjTJq5L6GZAn42/i5JzJ7EZ4jL64j9saBWSygYe2qJuuaResVSuIr60Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:49.843594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:199ba5cda6a509e19dba61f3d247ee903f13d3032e1fc660362186650acb7e75","sha256:b49e186faf68321e6aa1e4f05022c5b336f6aa631ff6f5bf2b49962d4b3fac36"],"state_sha256":"251f7ac2f16821bc01e00fcf3cc484ffe3c2f919e8911e7ad7cde16767cfba94"}