{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZSYNGQLOGVFK43RVQRV7T3PZ33","short_pith_number":"pith:ZSYNGQLO","canonical_record":{"source":{"id":"2607.22554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:45:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9345c5646aab6b74efc292c6ddb65449ff2462c45c49fc73be7d71ddbce3b270","abstract_canon_sha256":"72748cf9fb58f1ea00f73545869b39c5c32b2096c8cc508d4b09e5edfd64cec2"},"schema_version":"1.0"},"canonical_sha256":"ccb0d3416e354aae6e35846bf9edf9dedfb5bd0610d8d387b7921653751b8a95","source":{"kind":"arxiv","id":"2607.22554","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22554","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22554v1","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22554","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZSYNGQLOGVFK","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZSYNGQLOGVFK43RV","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZSYNGQLO","created_at":"2026-07-28T00:21:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZSYNGQLOGVFK43RVQRV7T3PZ33","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:45:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9345c5646aab6b74efc292c6ddb65449ff2462c45c49fc73be7d71ddbce3b270","abstract_canon_sha256":"72748cf9fb58f1ea00f73545869b39c5c32b2096c8cc508d4b09e5edfd64cec2"},"schema_version":"1.0"},"canonical_sha256":"ccb0d3416e354aae6e35846bf9edf9dedfb5bd0610d8d387b7921653751b8a95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:41.907262Z","signature_b64":"jnTRVVH7vAz/2qJD1m0YuLC7Lpn3sGZFIuadYT8sNCP86B4FO9NDyL1SBFMsTqsugkRYzT4zrono4UUkIa6FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb0d3416e354aae6e35846bf9edf9dedfb5bd0610d8d387b7921653751b8a95","last_reissued_at":"2026-07-28T00:21:41.906360Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:41.906360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22554","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":"2026-07-28T00:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l8S6p8mIu7/AB52gUqBVp73kfWpkH884SAnMBcZl7zzW/4erHWNK7ALlqV8m8H/utiTVNEM3jQU4PqG/sDl+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:41:55.798268Z"},"content_sha256":"d8ffdd0e64caafbb74fe5009dfe60ff1c1ce4b33292b6d37ab1f3cf4a1d5ebaa","schema_version":"1.0","event_id":"sha256:d8ffdd0e64caafbb74fe5009dfe60ff1c1ce4b33292b6d37ab1f3cf4a1d5ebaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZSYNGQLOGVFK43RVQRV7T3PZ33","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Armin Gerami, Kazem Faghih, Mobina Pournemat, Shoumik Saha, Soheil Feizi, Yize Cheng","submitted_at":"2026-05-18T16:45:13Z","abstract_excerpt":"Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways. In this work, we study how model answers change under meaning-preserving paraphrases across factual question answering and mathematical reasoning tasks. Across four benchmarks and 13 models, we find that model outputs frequently depend on the exact wording of the prompt. While overall accuracy typically changes only modestly across paraphrases, instance-level behavior is far less stable: for m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22554","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/2607.22554/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":"2026-07-28T00:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WBpo8YeFOJsZr7NOD/5E4q+IfsBgL1hY2L1zSvUY/Q1WQQrYtn3809tdkRsQywCYEygRq1vrDhnK9ct3i/XDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:41:55.798772Z"},"content_sha256":"96644993e8d1fad7cbffb5e8799687509f6d510f0e9f20f9fca45f2c75e4bc4b","schema_version":"1.0","event_id":"sha256:96644993e8d1fad7cbffb5e8799687509f6d510f0e9f20f9fca45f2c75e4bc4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/bundle.json","state_url":"https://pith.science/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/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":"2026-08-04T00:41:55Z","links":{"resolver":"https://pith.science/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33","bundle":"https://pith.science/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/bundle.json","state":"https://pith.science/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSYNGQLOGVFK43RVQRV7T3PZ33/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZSYNGQLOGVFK43RVQRV7T3PZ33","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":"72748cf9fb58f1ea00f73545869b39c5c32b2096c8cc508d4b09e5edfd64cec2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:45:13Z","title_canon_sha256":"9345c5646aab6b74efc292c6ddb65449ff2462c45c49fc73be7d71ddbce3b270"},"schema_version":"1.0","source":{"id":"2607.22554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22554","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22554v1","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22554","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZSYNGQLOGVFK","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZSYNGQLOGVFK43RV","created_at":"2026-07-28T00:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZSYNGQLO","created_at":"2026-07-28T00:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:96644993e8d1fad7cbffb5e8799687509f6d510f0e9f20f9fca45f2c75e4bc4b","target":"graph","created_at":"2026-07-28T00:21:41Z","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/2607.22554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways. In this work, we study how model answers change under meaning-preserving paraphrases across factual question answering and mathematical reasoning tasks. Across four benchmarks and 13 models, we find that model outputs frequently depend on the exact wording of the prompt. While overall accuracy typically changes only modestly across paraphrases, instance-level behavior is far less stable: for m","authors_text":"Armin Gerami, Kazem Faghih, Mobina Pournemat, Shoumik Saha, Soheil Feizi, Yize Cheng","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:45:13Z","title":"Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22554","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:d8ffdd0e64caafbb74fe5009dfe60ff1c1ce4b33292b6d37ab1f3cf4a1d5ebaa","target":"record","created_at":"2026-07-28T00:21:41Z","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":"72748cf9fb58f1ea00f73545869b39c5c32b2096c8cc508d4b09e5edfd64cec2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:45:13Z","title_canon_sha256":"9345c5646aab6b74efc292c6ddb65449ff2462c45c49fc73be7d71ddbce3b270"},"schema_version":"1.0","source":{"id":"2607.22554","kind":"arxiv","version":1}},"canonical_sha256":"ccb0d3416e354aae6e35846bf9edf9dedfb5bd0610d8d387b7921653751b8a95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb0d3416e354aae6e35846bf9edf9dedfb5bd0610d8d387b7921653751b8a95","first_computed_at":"2026-07-28T00:21:41.906360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:41.906360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jnTRVVH7vAz/2qJD1m0YuLC7Lpn3sGZFIuadYT8sNCP86B4FO9NDyL1SBFMsTqsugkRYzT4zrono4UUkIa6FCQ==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:41.907262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ffdd0e64caafbb74fe5009dfe60ff1c1ce4b33292b6d37ab1f3cf4a1d5ebaa","sha256:96644993e8d1fad7cbffb5e8799687509f6d510f0e9f20f9fca45f2c75e4bc4b"],"state_sha256":"aa02453fc98ab572328e8e347578ec1ac4c029e66384885366b0c72be992d447"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQ9GM9PmtpHRv9fAiKMOZJrYFnkn+LzbWbxTZpl4f3HcwQGoU2boaNO7Q6bpg9oTx3qDCjbUNj4ogD3EnACoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:41:55.802529Z","bundle_sha256":"8cf09a0a10a620d7dc707c4bc1ca20b95d06754d6f56221e80420f336eb2492a"}}