{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LCNZZCXLPWSMCSWTPPN6J6L5Z6","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":"e9f3cc38b8dd1a061fbf71a72f19c7e1cd5bd5a3072c6dd75a646a63a116c2d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:05:20Z","title_canon_sha256":"532733bd0a37b21d935c026b64d54368c0f0f7c0d82dd8ba8a7ee606207f6e7f"},"schema_version":"1.0","source":{"id":"2606.10657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10657","created_at":"2026-06-10T01:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10657v1","created_at":"2026-06-10T01:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10657","created_at":"2026-06-10T01:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"LCNZZCXLPWSM","created_at":"2026-06-10T01:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"LCNZZCXLPWSMCSWT","created_at":"2026-06-10T01:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"LCNZZCXL","created_at":"2026-06-10T01:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:7bbb2ecf874e6739ca67ec281fe20171f34784155b4b3f921c9d40d6465edb13","target":"graph","created_at":"2026-06-10T01:10:32Z","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/2606.10657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple-choice (MCQA) benchmarks are the standard for evaluating pretrained large language models, but their reliance on log-likelihood scoring makes them unreliable. Specifically, standard scores are highly sensitive to the exact phrasing (surface form) of the answers, conflating a model's familiarity with a specific phrase with its actual capability. We demonstrate this flaw using a controlled testbed of 1B-8B models trained on the same knowledge. Despite having identical knowledge, standard metrics falsely report a performance gap of over 2 points. To solve this, we propose ParaEval, an ev","authors_text":"Andrea Caciolai, Benjamin Piwowarski, Jo\\~ao Maria Janeiro, Loic Barrault, Mathurin Videau, Patrick Gallinari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:05:20Z","title":"Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10657","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":"sha256:9181a11985e30d569f203632af989ab9d36f418d89b082a404473c12be0adc11","target":"record","created_at":"2026-06-10T01:10:32Z","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":"e9f3cc38b8dd1a061fbf71a72f19c7e1cd5bd5a3072c6dd75a646a63a116c2d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:05:20Z","title_canon_sha256":"532733bd0a37b21d935c026b64d54368c0f0f7c0d82dd8ba8a7ee606207f6e7f"},"schema_version":"1.0","source":{"id":"2606.10657","kind":"arxiv","version":1}},"canonical_sha256":"589b9c8aeb7da4c14ad37bdbe4f97dcfbe51d330bb0a159e27c45568065ed87a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"589b9c8aeb7da4c14ad37bdbe4f97dcfbe51d330bb0a159e27c45568065ed87a","first_computed_at":"2026-06-10T01:10:32.784033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:32.784033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z3v4BQSFVhFa45YjhmTLfiISerGE3vEdzknOiZpbBFdPKTmkwIUjifx2m4pO6+NnxUJchN3+jhLiWFg4PLFhDw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:32.784934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9181a11985e30d569f203632af989ab9d36f418d89b082a404473c12be0adc11","sha256:7bbb2ecf874e6739ca67ec281fe20171f34784155b4b3f921c9d40d6465edb13"],"state_sha256":"2afe18032bc803c82da10801d26b1f89fa0917558fa756b0b785575c212f5757"}