{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZZDP63AGZIYGYRHHP3VSEMR4IJ","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":"8c3cd365caab552b0ada82e80dd2ddf56c5e2e4346f3eea75938f3cc362a83c0","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2023-08-07T18:04:12Z","title_canon_sha256":"8a315517b9e39e741eb3f1c228231ff8e01aa555cf0032d2c5cbdb91cd0b8f08"},"schema_version":"1.0","source":{"id":"2308.03854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03854","created_at":"2026-07-05T06:39:18Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03854v1","created_at":"2026-07-05T06:39:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03854","created_at":"2026-07-05T06:39:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZZDP63AGZIYG","created_at":"2026-07-05T06:39:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZZDP63AGZIYGYRHH","created_at":"2026-07-05T06:39:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZZDP63AG","created_at":"2026-07-05T06:39:18Z"}],"graph_snapshots":[{"event_id":"sha256:0cbf370130558684a7f4ca004792be2bb3153f1fb120534168486982f6203fe4","target":"graph","created_at":"2026-07-05T06:39:18Z","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/2308.03854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are incredibly powerful at comprehending and generating data in the form of text, but are brittle and error-prone. There has been an advent of toolkits and recipes centered around so-called prompt engineering-the process of asking an LLM to do something via a series of prompts. However, for LLM-powered data processing workflows, in particular, optimizing for quality, while keeping cost bounded, is a tedious, manual process. We put forth a vision for declarative prompt engineering. We view LLMs like crowd workers and leverage ideas from the declarative crowdsourcing","authors_text":"Aditya G. Parameswaran, Naman Jain, Parth Asawa, Shreya Shankar, Yujie Wang","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2023-08-07T18:04:12Z","title":"Revisiting Prompt Engineering via Declarative Crowdsourcing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03854","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":"sha256:9902c238ae270feb93b35f7d0a9856cba476178633c7f82bc94ae7b962f88027","target":"record","created_at":"2026-07-05T06:39:18Z","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":"8c3cd365caab552b0ada82e80dd2ddf56c5e2e4346f3eea75938f3cc362a83c0","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2023-08-07T18:04:12Z","title_canon_sha256":"8a315517b9e39e741eb3f1c228231ff8e01aa555cf0032d2c5cbdb91cd0b8f08"},"schema_version":"1.0","source":{"id":"2308.03854","kind":"arxiv","version":1}},"canonical_sha256":"ce46ff6c06ca306c44e77eeb22323c4279768e3d8c616df2d211337c5e29758c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce46ff6c06ca306c44e77eeb22323c4279768e3d8c616df2d211337c5e29758c","first_computed_at":"2026-07-05T06:39:18.289310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:18.289310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hwKjP0OY3gJiJegkPjIf6R/E+54lMzpUCNtRfxMrhPaEKv4/hb35Xxig2+bscpmOyhKJrzE10X5dizB2TtwsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:18.289801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.03854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9902c238ae270feb93b35f7d0a9856cba476178633c7f82bc94ae7b962f88027","sha256:0cbf370130558684a7f4ca004792be2bb3153f1fb120534168486982f6203fe4"],"state_sha256":"5e897a4438c5964e3b2f66be57fcaaca3ddab9a60d5283c1b9c0e51dc81309ad"}