{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RC5PKCBUDOSUMMVYH63GSZWR2W","short_pith_number":"pith:RC5PKCBU","canonical_record":{"source":{"id":"2410.12405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:38:13Z","cross_cats_sorted":[],"title_canon_sha256":"735e500f627580a8eaefb60ce3ea847741e313aacac78c361274d627b0e1368c","abstract_canon_sha256":"c0abbe4ae4aaa26ee3809421a9141fe995a355bcc65e049017f809f7e4e95230"},"schema_version":"1.0"},"canonical_sha256":"88baf508341ba54632b83fb66966d1d59f0c031df03fe96f20e6ba76a687e9e6","source":{"kind":"arxiv","id":"2410.12405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12405","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12405v1","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12405","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_12","alias_value":"RC5PKCBUDOSU","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_16","alias_value":"RC5PKCBUDOSUMMVY","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_8","alias_value":"RC5PKCBU","created_at":"2026-07-05T09:21:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RC5PKCBUDOSUMMVYH63GSZWR2W","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:38:13Z","cross_cats_sorted":[],"title_canon_sha256":"735e500f627580a8eaefb60ce3ea847741e313aacac78c361274d627b0e1368c","abstract_canon_sha256":"c0abbe4ae4aaa26ee3809421a9141fe995a355bcc65e049017f809f7e4e95230"},"schema_version":"1.0"},"canonical_sha256":"88baf508341ba54632b83fb66966d1d59f0c031df03fe96f20e6ba76a687e9e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:18.465849Z","signature_b64":"kcGp/7z2DIBIfO7cXkJcT7z//sWuBQ5KwDMnKSE003NvttdPLtJ/Hq+++35SyNMlL5vygVgDhmv1s7BvQK7mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88baf508341ba54632b83fb66966d1d59f0c031df03fe96f20e6ba76a687e9e6","last_reissued_at":"2026-07-05T09:21:18.465376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:18.465376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12405","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dPY4Pk7nZKO05X2oUzn//RTTJiLs2VX1l8Nwyn38yh9wuNNV4DvEwodc4+wKvafMaNLw+t5supTfSrSwlX79Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:15:06.569113Z"},"content_sha256":"7c2ee3652c882ab34858abb883729f9d8b3d6b261dcdf96a51810655b38495f6","schema_version":"1.0","event_id":"sha256:7c2ee3652c882ab34858abb883729f9d8b3d6b261dcdf96a51810655b38495f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RC5PKCBUDOSUMMVYH63GSZWR2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Haodong Duan, Jingming Zhuo, Kai Chen, Songyang Zhang, Xinyu Fang","submitted_at":"2024-10-16T09:38:13Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction. Current research frequently overlooks instance-level prompt variations and their implications on subjective evaluations. To address these shortcomings, we introduce ProSA, a framework designed to evaluate and comprehend prompt sensitivity in LLMs. ProSA incorporates a novel sensitivity metric, PromptSensiScore, and leverages decoding confidence to elucidate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12405","kind":"arxiv","version":1},"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/2410.12405/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":"2026-07-05T09:21:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTpmXf4cnDi9T0cZHU8Ooejp7hQQpW8ntkkqJHs2kGQViBoJ8fLjpDTbeYkczjGUmxA7bllXPpX7X77J4lcTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:15:06.569604Z"},"content_sha256":"346704bbfd7aa7ca3439d59bdcefc3b97614b81f01d45f2395454e3bc1f9bf18","schema_version":"1.0","event_id":"sha256:346704bbfd7aa7ca3439d59bdcefc3b97614b81f01d45f2395454e3bc1f9bf18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/bundle.json","state_url":"https://pith.science/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/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":"2026-08-06T03:15:06Z","links":{"resolver":"https://pith.science/pith/RC5PKCBUDOSUMMVYH63GSZWR2W","bundle":"https://pith.science/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/bundle.json","state":"https://pith.science/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RC5PKCBUDOSUMMVYH63GSZWR2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RC5PKCBUDOSUMMVYH63GSZWR2W","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":"c0abbe4ae4aaa26ee3809421a9141fe995a355bcc65e049017f809f7e4e95230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:38:13Z","title_canon_sha256":"735e500f627580a8eaefb60ce3ea847741e313aacac78c361274d627b0e1368c"},"schema_version":"1.0","source":{"id":"2410.12405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12405","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12405v1","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12405","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_12","alias_value":"RC5PKCBUDOSU","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_16","alias_value":"RC5PKCBUDOSUMMVY","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_8","alias_value":"RC5PKCBU","created_at":"2026-07-05T09:21:18Z"}],"graph_snapshots":[{"event_id":"sha256:346704bbfd7aa7ca3439d59bdcefc3b97614b81f01d45f2395454e3bc1f9bf18","target":"graph","created_at":"2026-07-05T09:21:18Z","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/2410.12405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction. Current research frequently overlooks instance-level prompt variations and their implications on subjective evaluations. To address these shortcomings, we introduce ProSA, a framework designed to evaluate and comprehend prompt sensitivity in LLMs. ProSA incorporates a novel sensitivity metric, PromptSensiScore, and leverages decoding confidence to elucidate","authors_text":"Dahua Lin, Haodong Duan, Jingming Zhuo, Kai Chen, Songyang Zhang, Xinyu Fang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:38:13Z","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12405","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":"sha256:7c2ee3652c882ab34858abb883729f9d8b3d6b261dcdf96a51810655b38495f6","target":"record","created_at":"2026-07-05T09:21:18Z","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":"c0abbe4ae4aaa26ee3809421a9141fe995a355bcc65e049017f809f7e4e95230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:38:13Z","title_canon_sha256":"735e500f627580a8eaefb60ce3ea847741e313aacac78c361274d627b0e1368c"},"schema_version":"1.0","source":{"id":"2410.12405","kind":"arxiv","version":1}},"canonical_sha256":"88baf508341ba54632b83fb66966d1d59f0c031df03fe96f20e6ba76a687e9e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88baf508341ba54632b83fb66966d1d59f0c031df03fe96f20e6ba76a687e9e6","first_computed_at":"2026-07-05T09:21:18.465376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:18.465376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kcGp/7z2DIBIfO7cXkJcT7z//sWuBQ5KwDMnKSE003NvttdPLtJ/Hq+++35SyNMlL5vygVgDhmv1s7BvQK7mAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:18.465849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c2ee3652c882ab34858abb883729f9d8b3d6b261dcdf96a51810655b38495f6","sha256:346704bbfd7aa7ca3439d59bdcefc3b97614b81f01d45f2395454e3bc1f9bf18"],"state_sha256":"57ccc124ee6ffd0f60a5aff951302d4afd09719479ea2c47515a805011c195c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOOz3UHp4A+BACKS8mUJIjUnBoRI+y+fycPOpfp6DCXgm5Ycnu0ixvvuAmpOH4RyFDr8bpue+voL2GP68dlZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:15:06.574254Z","bundle_sha256":"7cb16ae70bf4977f6ce31f995001ba14e7cc80aee8065bc1daf0a8a63805c24d"}}