{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XXU4AYPSQ6DT7XBSKGITW4QQA3","short_pith_number":"pith:XXU4AYPS","canonical_record":{"source":{"id":"2502.14127","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T22:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"4b8782f69ceaee5ffe3afc5a823d26ea23aad9e261e3d6ae6355aab702cbedbe","abstract_canon_sha256":"58d5027a3249ad111a4f3a665e64af4f2c6206ca0f59dc453227ec703aceeb12"},"schema_version":"1.0"},"canonical_sha256":"bde9c061f287873fdc3251913b721006e09649dd3df7b4268f9e01bc10dfa8ed","source":{"kind":"arxiv","id":"2502.14127","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14127","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14127v2","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14127","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"XXU4AYPSQ6DT","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"XXU4AYPSQ6DT7XBS","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"XXU4AYPS","created_at":"2026-07-05T11:13:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XXU4AYPSQ6DT7XBSKGITW4QQA3","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14127","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T22:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"4b8782f69ceaee5ffe3afc5a823d26ea23aad9e261e3d6ae6355aab702cbedbe","abstract_canon_sha256":"58d5027a3249ad111a4f3a665e64af4f2c6206ca0f59dc453227ec703aceeb12"},"schema_version":"1.0"},"canonical_sha256":"bde9c061f287873fdc3251913b721006e09649dd3df7b4268f9e01bc10dfa8ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:21.038651Z","signature_b64":"9gNKZ9S62NPhNr2wyYWBzLdxJqp4DPdndEBnsTquLgWBhMnE8bTAedppaPDwurt+yZ3VHNAU0vvGPHHUVeAoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bde9c061f287873fdc3251913b721006e09649dd3df7b4268f9e01bc10dfa8ed","last_reissued_at":"2026-07-05T11:13:21.038096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:21.038096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14127","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZ4zhNxNrnoVBxqw0dGDEqGYE5r6jkqF9Sg/eKGyQ2N45Y6djI/z/lMNpMhjPVUVoMEJ64hjh1MXZXnhMXQOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:55:01.287323Z"},"content_sha256":"ed90918499462658338ee22ef668a7cd90e3edfe6241bb9f179ef4e8e622e910","schema_version":"1.0","event_id":"sha256:ed90918499462658338ee22ef668a7cd90e3edfe6241bb9f179ef4e8e622e910"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XXU4AYPSQ6DT7XBSKGITW4QQA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jordan Lee Boyd-Graber, Nishant Balepur, Rachel Rudinger","submitted_at":"2025-02-19T22:11:52Z","abstract_excerpt":"Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity; 2) match LLM use cases; and 3) fully test knowledge. We instead advocate for generative formats based on human testing, where LLMs construct and explain answers, better capturing user needs and knowledge while remaining easy to score. We then show even when MCQA is a useful format, its datasets suffer from: leakage; unanswerability; shortcuts; and saturation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14127","kind":"arxiv","version":2},"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/2502.14127/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":"2026-07-05T11:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1yq7yGsuLXTG/GW0c/+rF0xW8gUw/55mnvUdKesTz8D7i9oOPQm7EQjOnfYV1LaVeYXNFSYMYoWck04rQ7tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:55:01.288274Z"},"content_sha256":"e3cf157ac938b8794f14243129d13cf5b9b5a1fadc8baaa115e780c1448e06b0","schema_version":"1.0","event_id":"sha256:e3cf157ac938b8794f14243129d13cf5b9b5a1fadc8baaa115e780c1448e06b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/bundle.json","state_url":"https://pith.science/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/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":"2026-08-17T06:55:01Z","links":{"resolver":"https://pith.science/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3","bundle":"https://pith.science/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/bundle.json","state":"https://pith.science/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXU4AYPSQ6DT7XBSKGITW4QQA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XXU4AYPSQ6DT7XBSKGITW4QQA3","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":"58d5027a3249ad111a4f3a665e64af4f2c6206ca0f59dc453227ec703aceeb12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T22:11:52Z","title_canon_sha256":"4b8782f69ceaee5ffe3afc5a823d26ea23aad9e261e3d6ae6355aab702cbedbe"},"schema_version":"1.0","source":{"id":"2502.14127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14127","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14127v2","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14127","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"XXU4AYPSQ6DT","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"XXU4AYPSQ6DT7XBS","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"XXU4AYPS","created_at":"2026-07-05T11:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:e3cf157ac938b8794f14243129d13cf5b9b5a1fadc8baaa115e780c1448e06b0","target":"graph","created_at":"2026-07-05T11:13:21Z","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/2502.14127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity; 2) match LLM use cases; and 3) fully test knowledge. We instead advocate for generative formats based on human testing, where LLMs construct and explain answers, better capturing user needs and knowledge while remaining easy to score. We then show even when MCQA is a useful format, its datasets suffer from: leakage; unanswerability; shortcuts; and saturation","authors_text":"Jordan Lee Boyd-Graber, Nishant Balepur, Rachel Rudinger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T22:11:52Z","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14127","kind":"arxiv","version":2},"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:ed90918499462658338ee22ef668a7cd90e3edfe6241bb9f179ef4e8e622e910","target":"record","created_at":"2026-07-05T11:13:21Z","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":"58d5027a3249ad111a4f3a665e64af4f2c6206ca0f59dc453227ec703aceeb12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T22:11:52Z","title_canon_sha256":"4b8782f69ceaee5ffe3afc5a823d26ea23aad9e261e3d6ae6355aab702cbedbe"},"schema_version":"1.0","source":{"id":"2502.14127","kind":"arxiv","version":2}},"canonical_sha256":"bde9c061f287873fdc3251913b721006e09649dd3df7b4268f9e01bc10dfa8ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bde9c061f287873fdc3251913b721006e09649dd3df7b4268f9e01bc10dfa8ed","first_computed_at":"2026-07-05T11:13:21.038096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:21.038096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9gNKZ9S62NPhNr2wyYWBzLdxJqp4DPdndEBnsTquLgWBhMnE8bTAedppaPDwurt+yZ3VHNAU0vvGPHHUVeAoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:21.038651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed90918499462658338ee22ef668a7cd90e3edfe6241bb9f179ef4e8e622e910","sha256:e3cf157ac938b8794f14243129d13cf5b9b5a1fadc8baaa115e780c1448e06b0"],"state_sha256":"4f4d5b623b7945c3ad854e7a20b3981d5f732bebb37af1ee4ad705c873279ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WCmHOh7nlo/guYrfWklQc2OJVSNHJu+IPKMkN7AfOKGw3X+iQkd6lPulRp7qxOWTKc9GWrdJ1apuobcTsJ+4AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:55:01.293666Z","bundle_sha256":"fe9ffdc466b12b98e5f9999817361291e1519bb46d3c5b0f865911942dbf3b4d"}}