{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6EDBOHMWVUJ2TAGDYLQW4FDXVE","short_pith_number":"pith:6EDBOHMW","canonical_record":{"source":{"id":"2503.00137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"bb81b753f87ea94b9be74453699dfc1f994139dcb9f2782bdc0b00b544b6a270","abstract_canon_sha256":"b6e42ecedc79fe89139694d2817d49df4753043070909b60fc493e46d5ae93e2"},"schema_version":"1.0"},"canonical_sha256":"f106171d96ad13a980c3c2e16e1477a93764e67c49204c11e887f60a79668a9b","source":{"kind":"arxiv","id":"2503.00137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00137","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00137v1","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00137","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"6EDBOHMWVUJ2","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"6EDBOHMWVUJ2TAGD","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"6EDBOHMW","created_at":"2026-07-05T10:22:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6EDBOHMWVUJ2TAGDYLQW4FDXVE","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"bb81b753f87ea94b9be74453699dfc1f994139dcb9f2782bdc0b00b544b6a270","abstract_canon_sha256":"b6e42ecedc79fe89139694d2817d49df4753043070909b60fc493e46d5ae93e2"},"schema_version":"1.0"},"canonical_sha256":"f106171d96ad13a980c3c2e16e1477a93764e67c49204c11e887f60a79668a9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:17.863896Z","signature_b64":"vDl2Yii7hSt9M3mgHTzgPopiUQBbipT9SnddH3fu3bbfOjA4Ydddkdl35lZUeyfBmvD2WKm/+mLwcLQ2w+J3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f106171d96ad13a980c3c2e16e1477a93764e67c49204c11e887f60a79668a9b","last_reissued_at":"2026-07-05T10:22:17.863279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:17.863279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00137","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":"2026-07-05T10:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FGv1VxF1+sVWJIcjskgGfXVJZer6Fa49quhyJ5L21XLK54b76vGp3CEP1uLQAdqr+KgONj8YeGyXzpRYRUvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T01:24:33.296923Z"},"content_sha256":"f3a3b584da0ba064a900a47acc95c88c5757d27926a9b4399b33d3fd7e501386","schema_version":"1.0","event_id":"sha256:f3a3b584da0ba064a900a47acc95c88c5757d27926a9b4399b33d3fd7e501386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6EDBOHMWVUJ2TAGDYLQW4FDXVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Evelina Bakhturina, Grigor Nalbandyan, Rima Shahbazyan","submitted_at":"2025-02-28T19:27:29Z","abstract_excerpt":"Typical evaluations of Large Language Models (LLMs) report a single metric per dataset, often representing the model's best-case performance under carefully selected settings. Unfortunately, this approach overlooks model robustness and reliability in real-world applications. For instance, simple paraphrasing of prompts on the MMLU-Pro dataset causes accuracy fluctuations of up to 10\\%, while reordering answer choices in the AGIEval dataset results in accuracy differences of up to 6.1\\%. While some studies discuss issues with LLM robustness, there is no unified or centralized framework for eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00137","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/2503.00137/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":"2026-07-05T10:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E37bzRqFpVQoJv39Q4W3gzSu5MeLm1p4qrVjCKG/Vjg9ZwR5kc1emKpVxKr+KUox1WxZc1Df+4r3tyhiPb3oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T01:24:33.297303Z"},"content_sha256":"686d1bfd802d9d452edfaf46f710fcd0de6312e094a40aa8e5548157268e0b7b","schema_version":"1.0","event_id":"sha256:686d1bfd802d9d452edfaf46f710fcd0de6312e094a40aa8e5548157268e0b7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/bundle.json","state_url":"https://pith.science/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/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":"2026-07-27T01:24:33Z","links":{"resolver":"https://pith.science/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE","bundle":"https://pith.science/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/bundle.json","state":"https://pith.science/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EDBOHMWVUJ2TAGDYLQW4FDXVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6EDBOHMWVUJ2TAGDYLQW4FDXVE","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":"b6e42ecedc79fe89139694d2817d49df4753043070909b60fc493e46d5ae93e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:27:29Z","title_canon_sha256":"bb81b753f87ea94b9be74453699dfc1f994139dcb9f2782bdc0b00b544b6a270"},"schema_version":"1.0","source":{"id":"2503.00137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00137","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00137v1","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00137","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"6EDBOHMWVUJ2","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"6EDBOHMWVUJ2TAGD","created_at":"2026-07-05T10:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"6EDBOHMW","created_at":"2026-07-05T10:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:686d1bfd802d9d452edfaf46f710fcd0de6312e094a40aa8e5548157268e0b7b","target":"graph","created_at":"2026-07-05T10:22:17Z","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/2503.00137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Typical evaluations of Large Language Models (LLMs) report a single metric per dataset, often representing the model's best-case performance under carefully selected settings. Unfortunately, this approach overlooks model robustness and reliability in real-world applications. For instance, simple paraphrasing of prompts on the MMLU-Pro dataset causes accuracy fluctuations of up to 10\\%, while reordering answer choices in the AGIEval dataset results in accuracy differences of up to 6.1\\%. While some studies discuss issues with LLM robustness, there is no unified or centralized framework for eval","authors_text":"Evelina Bakhturina, Grigor Nalbandyan, Rima Shahbazyan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:27:29Z","title":"SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00137","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:f3a3b584da0ba064a900a47acc95c88c5757d27926a9b4399b33d3fd7e501386","target":"record","created_at":"2026-07-05T10:22:17Z","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":"b6e42ecedc79fe89139694d2817d49df4753043070909b60fc493e46d5ae93e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:27:29Z","title_canon_sha256":"bb81b753f87ea94b9be74453699dfc1f994139dcb9f2782bdc0b00b544b6a270"},"schema_version":"1.0","source":{"id":"2503.00137","kind":"arxiv","version":1}},"canonical_sha256":"f106171d96ad13a980c3c2e16e1477a93764e67c49204c11e887f60a79668a9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f106171d96ad13a980c3c2e16e1477a93764e67c49204c11e887f60a79668a9b","first_computed_at":"2026-07-05T10:22:17.863279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:17.863279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vDl2Yii7hSt9M3mgHTzgPopiUQBbipT9SnddH3fu3bbfOjA4Ydddkdl35lZUeyfBmvD2WKm/+mLwcLQ2w+J3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:17.863896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3a3b584da0ba064a900a47acc95c88c5757d27926a9b4399b33d3fd7e501386","sha256:686d1bfd802d9d452edfaf46f710fcd0de6312e094a40aa8e5548157268e0b7b"],"state_sha256":"1a8aa514cf338f99d63ccd8ac77088d2f3bfbae5f4cfeb2ed32067e505721dd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+MJKJWnVflxzEaYQPCl4V2vAGIdnJxDCTFgOWuxj8+ChZyfrRsiGTEDgFGnampYL1ra1YKo80rxZ9BQFNLFzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T01:24:33.299982Z","bundle_sha256":"1a4d1a0da56658b7a739334769d09ace3d1ed6903a615c7c249c09bb85725ef0"}}