{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3JROBPOHFX5W5UK33ND2GCLB27","short_pith_number":"pith:3JROBPOH","canonical_record":{"source":{"id":"2502.06065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T23:01:03Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"2d9043a8f5483593e2e5697fcb2aea599dca87e794ed3c2a08dcab3d332309f6","abstract_canon_sha256":"90a92a0e74803321c6a5e1cd25176bc49b2d74eb34df90673693444e99cc6fcd"},"schema_version":"1.0"},"canonical_sha256":"da62e0bdc72dfb6ed15bdb47a30961d7edaf59205736f2b59864004ba8b3ed1b","source":{"kind":"arxiv","id":"2502.06065","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06065","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06065v1","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06065","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"3JROBPOHFX5W","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"3JROBPOHFX5W5UK3","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"3JROBPOH","created_at":"2026-07-05T10:11:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3JROBPOHFX5W5UK33ND2GCLB27","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T23:01:03Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"2d9043a8f5483593e2e5697fcb2aea599dca87e794ed3c2a08dcab3d332309f6","abstract_canon_sha256":"90a92a0e74803321c6a5e1cd25176bc49b2d74eb34df90673693444e99cc6fcd"},"schema_version":"1.0"},"canonical_sha256":"da62e0bdc72dfb6ed15bdb47a30961d7edaf59205736f2b59864004ba8b3ed1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:47.218940Z","signature_b64":"k7ACr2R5Eepc9Y5wWHOlhGz+ZATFTVdEtbExGPxGUbqr3Jx+PxQkY4SvsK7vBrl0MqV6Yy2QXd4yf2LKONoaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da62e0bdc72dfb6ed15bdb47a30961d7edaf59205736f2b59864004ba8b3ed1b","last_reissued_at":"2026-07-05T10:11:47.218379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:47.218379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06065","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":"2026-07-05T10:11:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7I7VjDkJ542jM2n+HKQdJzTrZ8yskVb8hURQd5mC48+yp6q38ewMDNfVzRTgs3wmFtws+O2vFitatJa6WoHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:47.487034Z"},"content_sha256":"69043112b75c4c18595c02ccc0e240ef496d0354bba827bdfc4dc695cc6cb87d","schema_version":"1.0","event_id":"sha256:69043112b75c4c18595c02ccc0e240ef496d0354bba827bdfc4dc695cc6cb87d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3JROBPOHFX5W5UK33ND2GCLB27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Prompt Sensitivity in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Amirhossein Razavi, Ebrahim Bagheri, Mina Soltangheis, Morteza Zihayat, Negar Arabzadeh, Sara Salamat","submitted_at":"2025-02-09T23:01:03Z","abstract_excerpt":"Large language Models (LLMs) are highly sensitive to variations in prompt formulation, which can significantly impact their ability to generate accurate responses. In this paper, we introduce a new task, Prompt Sensitivity Prediction, and a dataset PromptSET designed to investigate the effects of slight prompt variations on LLM performance. Using TriviaQA and HotpotQA datasets as the foundation of our work, we generate prompt variations and evaluate their effectiveness across multiple LLMs. We benchmark the prompt sensitivity prediction task employing state-of-the-art methods from related task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06065","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/2502.06065/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":"2026-07-05T10:11:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28dAs5i+A4F5jSgCyGwbNyQMHZqS1t8qtYjMXov8Ym8y6tBeklm6s50rUfHFWDQdVL/l0te14Lv3W4Htp4ohAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:47.487564Z"},"content_sha256":"c21c69abe3aebec04b601b6a48bc2f8338c82ba164e0f51427b9da6b2f8dbc2e","schema_version":"1.0","event_id":"sha256:c21c69abe3aebec04b601b6a48bc2f8338c82ba164e0f51427b9da6b2f8dbc2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JROBPOHFX5W5UK33ND2GCLB27/bundle.json","state_url":"https://pith.science/pith/3JROBPOHFX5W5UK33ND2GCLB27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JROBPOHFX5W5UK33ND2GCLB27/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":"2026-08-09T07:48:47Z","links":{"resolver":"https://pith.science/pith/3JROBPOHFX5W5UK33ND2GCLB27","bundle":"https://pith.science/pith/3JROBPOHFX5W5UK33ND2GCLB27/bundle.json","state":"https://pith.science/pith/3JROBPOHFX5W5UK33ND2GCLB27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JROBPOHFX5W5UK33ND2GCLB27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3JROBPOHFX5W5UK33ND2GCLB27","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":"90a92a0e74803321c6a5e1cd25176bc49b2d74eb34df90673693444e99cc6fcd","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T23:01:03Z","title_canon_sha256":"2d9043a8f5483593e2e5697fcb2aea599dca87e794ed3c2a08dcab3d332309f6"},"schema_version":"1.0","source":{"id":"2502.06065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06065","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06065v1","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06065","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"3JROBPOHFX5W","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"3JROBPOHFX5W5UK3","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"3JROBPOH","created_at":"2026-07-05T10:11:47Z"}],"graph_snapshots":[{"event_id":"sha256:c21c69abe3aebec04b601b6a48bc2f8338c82ba164e0f51427b9da6b2f8dbc2e","target":"graph","created_at":"2026-07-05T10:11:47Z","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/2502.06065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language Models (LLMs) are highly sensitive to variations in prompt formulation, which can significantly impact their ability to generate accurate responses. In this paper, we introduce a new task, Prompt Sensitivity Prediction, and a dataset PromptSET designed to investigate the effects of slight prompt variations on LLM performance. Using TriviaQA and HotpotQA datasets as the foundation of our work, we generate prompt variations and evaluate their effectiveness across multiple LLMs. We benchmark the prompt sensitivity prediction task employing state-of-the-art methods from related task","authors_text":"Amirhossein Razavi, Ebrahim Bagheri, Mina Soltangheis, Morteza Zihayat, Negar Arabzadeh, Sara Salamat","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T23:01:03Z","title":"Benchmarking Prompt Sensitivity in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06065","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":"sha256:69043112b75c4c18595c02ccc0e240ef496d0354bba827bdfc4dc695cc6cb87d","target":"record","created_at":"2026-07-05T10:11:47Z","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":"90a92a0e74803321c6a5e1cd25176bc49b2d74eb34df90673693444e99cc6fcd","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T23:01:03Z","title_canon_sha256":"2d9043a8f5483593e2e5697fcb2aea599dca87e794ed3c2a08dcab3d332309f6"},"schema_version":"1.0","source":{"id":"2502.06065","kind":"arxiv","version":1}},"canonical_sha256":"da62e0bdc72dfb6ed15bdb47a30961d7edaf59205736f2b59864004ba8b3ed1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da62e0bdc72dfb6ed15bdb47a30961d7edaf59205736f2b59864004ba8b3ed1b","first_computed_at":"2026-07-05T10:11:47.218379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:47.218379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7ACr2R5Eepc9Y5wWHOlhGz+ZATFTVdEtbExGPxGUbqr3Jx+PxQkY4SvsK7vBrl0MqV6Yy2QXd4yf2LKONoaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:47.218940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69043112b75c4c18595c02ccc0e240ef496d0354bba827bdfc4dc695cc6cb87d","sha256:c21c69abe3aebec04b601b6a48bc2f8338c82ba164e0f51427b9da6b2f8dbc2e"],"state_sha256":"d108feddd3ba184827c484630499b4bfbadc5fec8e0e9fca82de69b915460be5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXt+G6S5e+87+FanIxsd0Bd0bUCF08etExOpE0EKmjhmLDoqiaE6yXUPNny+sFuuglKbZ19wbBQNQREKGiM+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:48:47.492538Z","bundle_sha256":"78fae4079eb4381043c773d6463c9098dea808bca8b1022664bf83aeb2ba363a"}}