{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VHKYNHJDNZYHV4EDWGX7NJXUY6","short_pith_number":"pith:VHKYNHJD","canonical_record":{"source":{"id":"2407.02039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T08:11:18Z","cross_cats_sorted":[],"title_canon_sha256":"320908346f3674c7f772cf3e9352e02e49592b526817aee5b5eae359ef4b7a3e","abstract_canon_sha256":"16072593368e70a394f421db7e898b0d19d34cbb0348d5571af5ae84c3bf4ae2"},"schema_version":"1.0"},"canonical_sha256":"a9d5869d236e707af083b1aff6a6f4c7938f9256a000642876f635d7c7155fdd","source":{"kind":"arxiv","id":"2407.02039","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02039","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02039v3","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02039","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_12","alias_value":"VHKYNHJDNZYH","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_16","alias_value":"VHKYNHJDNZYHV4ED","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_8","alias_value":"VHKYNHJD","created_at":"2026-05-20T00:00:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VHKYNHJDNZYHV4EDWGX7NJXUY6","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T08:11:18Z","cross_cats_sorted":[],"title_canon_sha256":"320908346f3674c7f772cf3e9352e02e49592b526817aee5b5eae359ef4b7a3e","abstract_canon_sha256":"16072593368e70a394f421db7e898b0d19d34cbb0348d5571af5ae84c3bf4ae2"},"schema_version":"1.0"},"canonical_sha256":"a9d5869d236e707af083b1aff6a6f4c7938f9256a000642876f635d7c7155fdd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:15.756644Z","signature_b64":"QJrxcal9Amj7/Ag1ADXLHNGHgLSKCW3W/nIZpZvDOt9md4rQ8NQMQSZt/X+ZsN2ziZ2mFZEnKCwm3lOlMxTkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d5869d236e707af083b1aff6a6f4c7938f9256a000642876f635d7c7155fdd","last_reissued_at":"2026-05-20T00:00:15.755906Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:15.755906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02039","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbdxtDrQxGeIIW3Pq8cDYS4zepahCDdsLqMQHNc81BaEnVo3486X6x49zwWtXdxVj1HZ5bkrFmK+ItzgUwSjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:54:34.752928Z"},"content_sha256":"bc4f541ab0d60008141d0324c83e37ee0a7b40e17da06ce8b6ac9222ef41600a","schema_version":"1.0","event_id":"sha256:bc4f541ab0d60008141d0324c83e37ee0a7b40e17da06ce8b6ac9222ef41600a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VHKYNHJDNZYHV4EDWGX7NJXUY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt Stability Scoring for Text Annotation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Barrie, Elli Palaiologou, Petter T\\\"ornberg","submitted_at":"2024-07-02T08:11:18Z","abstract_excerpt":"Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The reproducibility of LM outputs may nonetheless be vulnerable to small changes in the prompt design. This calls into question the replicability of classification routines. To tackle this problem, researchers have typically tested a variety of semantically similar prompts to determine what we call ``prompt stability.\" These approaches remain ad-hoc and task specific. In this article, we propose a gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02039","kind":"arxiv","version":3},"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/2407.02039/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMORUXMIMbHpdWC+UUG1YB4mJXW8or2+Wm7RywX8BcrHfH/8kXux5tg31kv8lYXBMQyqp2DGXk/ISUxNcm2LCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:54:34.753717Z"},"content_sha256":"c7d3a9402f2efd52e6b85eb9bc1bd73400b45eef09d9f1579ba30d2df9db8248","schema_version":"1.0","event_id":"sha256:c7d3a9402f2efd52e6b85eb9bc1bd73400b45eef09d9f1579ba30d2df9db8248"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/bundle.json","state_url":"https://pith.science/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T16:54:34Z","links":{"resolver":"https://pith.science/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6","bundle":"https://pith.science/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/bundle.json","state":"https://pith.science/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHKYNHJDNZYHV4EDWGX7NJXUY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHKYNHJDNZYHV4EDWGX7NJXUY6","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":"16072593368e70a394f421db7e898b0d19d34cbb0348d5571af5ae84c3bf4ae2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T08:11:18Z","title_canon_sha256":"320908346f3674c7f772cf3e9352e02e49592b526817aee5b5eae359ef4b7a3e"},"schema_version":"1.0","source":{"id":"2407.02039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02039","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02039v3","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02039","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_12","alias_value":"VHKYNHJDNZYH","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_16","alias_value":"VHKYNHJDNZYHV4ED","created_at":"2026-05-20T00:00:15Z"},{"alias_kind":"pith_short_8","alias_value":"VHKYNHJD","created_at":"2026-05-20T00:00:15Z"}],"graph_snapshots":[{"event_id":"sha256:c7d3a9402f2efd52e6b85eb9bc1bd73400b45eef09d9f1579ba30d2df9db8248","target":"graph","created_at":"2026-05-20T00:00:15Z","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/2407.02039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The reproducibility of LM outputs may nonetheless be vulnerable to small changes in the prompt design. This calls into question the replicability of classification routines. To tackle this problem, researchers have typically tested a variety of semantically similar prompts to determine what we call ``prompt stability.\" These approaches remain ad-hoc and task specific. In this article, we propose a gen","authors_text":"Christopher Barrie, Elli Palaiologou, Petter T\\\"ornberg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T08:11:18Z","title":"Prompt Stability Scoring for Text Annotation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02039","kind":"arxiv","version":3},"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:bc4f541ab0d60008141d0324c83e37ee0a7b40e17da06ce8b6ac9222ef41600a","target":"record","created_at":"2026-05-20T00:00:15Z","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":"16072593368e70a394f421db7e898b0d19d34cbb0348d5571af5ae84c3bf4ae2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T08:11:18Z","title_canon_sha256":"320908346f3674c7f772cf3e9352e02e49592b526817aee5b5eae359ef4b7a3e"},"schema_version":"1.0","source":{"id":"2407.02039","kind":"arxiv","version":3}},"canonical_sha256":"a9d5869d236e707af083b1aff6a6f4c7938f9256a000642876f635d7c7155fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9d5869d236e707af083b1aff6a6f4c7938f9256a000642876f635d7c7155fdd","first_computed_at":"2026-05-20T00:00:15.755906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:15.755906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJrxcal9Amj7/Ag1ADXLHNGHgLSKCW3W/nIZpZvDOt9md4rQ8NQMQSZt/X+ZsN2ziZ2mFZEnKCwm3lOlMxTkDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:15.756644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc4f541ab0d60008141d0324c83e37ee0a7b40e17da06ce8b6ac9222ef41600a","sha256:c7d3a9402f2efd52e6b85eb9bc1bd73400b45eef09d9f1579ba30d2df9db8248"],"state_sha256":"d4d37b854db2f79fefd1832b569c4078d4daf76592d6432e103400ccc8ddd025"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqk5AGD3bifuzdFNPqkqdakbObu/IkGN12nVWpe1ldAXp99CIF/gofxPkHoc3Rw1YWgZ4flv8aYG30ZYYj1uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:54:34.757753Z","bundle_sha256":"f0791e448618d22eec0569293d18f2ad3c52d910813c92e77cab4dbd285f9c97"}}