{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4UJ4DGFII7LUPVCRIBRL55X3F6","short_pith_number":"pith:4UJ4DGFI","canonical_record":{"source":{"id":"2504.07825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T15:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"95228dce548b1e43a5cca17fe1de4008a71ecb8631a421d3b0b1c2f3c5dd01a3","abstract_canon_sha256":"1a35559ac0ab74691d1804465c32cdbb38c95063356f8b96f325371238e4cf6f"},"schema_version":"1.0"},"canonical_sha256":"e513c198a847d747d4514062bef6fb2f8763fe838132b21e1fb7ef9bd6fed424","source":{"kind":"arxiv","id":"2504.07825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07825","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07825v1","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07825","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"4UJ4DGFII7LU","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"4UJ4DGFII7LUPVCR","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"4UJ4DGFI","created_at":"2026-07-05T10:47:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4UJ4DGFII7LUPVCRIBRL55X3F6","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T15:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"95228dce548b1e43a5cca17fe1de4008a71ecb8631a421d3b0b1c2f3c5dd01a3","abstract_canon_sha256":"1a35559ac0ab74691d1804465c32cdbb38c95063356f8b96f325371238e4cf6f"},"schema_version":"1.0"},"canonical_sha256":"e513c198a847d747d4514062bef6fb2f8763fe838132b21e1fb7ef9bd6fed424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:15.432575Z","signature_b64":"i47F/PQYSo32Lh/TAKlp8SscgYAPpqYx4FbGexYDgn/v9Z/A2KLyx2Hc3Uj7/uaS12WzIGo64g4KTaU5IxvrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e513c198a847d747d4514062bef6fb2f8763fe838132b21e1fb7ef9bd6fed424","last_reissued_at":"2026-07-05T10:47:15.432084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:15.432084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07825","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":"2026-07-05T10:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfBBHYSzG4wKyGk7OzTN69F+8KbT4ft3yAAS4MC0LLSyUcUeCJy758Syy9Cji0r9ZIOEtHeBHTuRsD393dW+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:17:01.225339Z"},"content_sha256":"1d423955b0168e5c456fd6056b6f3e91cbcd1bf30d0f964977852a6574f402cb","schema_version":"1.0","event_id":"sha256:1d423955b0168e5c456fd6056b6f3e91cbcd1bf30d0f964977852a6574f402cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4UJ4DGFII7LUPVCRIBRL55X3F6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan P. Yamshchikov, Mattia Nee, Pavel Chizhov, Pierre-Carl Langlais","submitted_at":"2025-04-10T15:01:46Z","abstract_excerpt":"Common-sense reasoning is a key language model capability because it encapsulates not just specific factual knowledge but rather general language and world understanding. Measuring common-sense reasoning, therefore, is crucial for language models of different sizes and applications. One of the most widely used benchmarks for evaluating such capabilities is HellaSwag; however, in this paper, we show that it has severe construct validity issues. These issues range from basic ungrammaticality and numerous typos to misleading prompts or equally correct options. Furthermore, we show that if models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07825","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/2504.07825/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":"2026-07-05T10:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xPNeZ0KrtyyqnjS4hRjMCC9JooKKp7/4eUF4u3Hx5yIRjci8lLuCDLKCcWYrSQkFrtu/vonP86DGqWMHr4qiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:17:01.225723Z"},"content_sha256":"249dca773b58969863b0fa5f9e73465c237abe7aa5cf5f202ffe11ad73540cca","schema_version":"1.0","event_id":"sha256:249dca773b58969863b0fa5f9e73465c237abe7aa5cf5f202ffe11ad73540cca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/bundle.json","state_url":"https://pith.science/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/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":"2026-07-06T20:17:01Z","links":{"resolver":"https://pith.science/pith/4UJ4DGFII7LUPVCRIBRL55X3F6","bundle":"https://pith.science/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/bundle.json","state":"https://pith.science/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UJ4DGFII7LUPVCRIBRL55X3F6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4UJ4DGFII7LUPVCRIBRL55X3F6","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":"1a35559ac0ab74691d1804465c32cdbb38c95063356f8b96f325371238e4cf6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T15:01:46Z","title_canon_sha256":"95228dce548b1e43a5cca17fe1de4008a71ecb8631a421d3b0b1c2f3c5dd01a3"},"schema_version":"1.0","source":{"id":"2504.07825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07825","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07825v1","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07825","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"4UJ4DGFII7LU","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"4UJ4DGFII7LUPVCR","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"4UJ4DGFI","created_at":"2026-07-05T10:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:249dca773b58969863b0fa5f9e73465c237abe7aa5cf5f202ffe11ad73540cca","target":"graph","created_at":"2026-07-05T10:47:15Z","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/2504.07825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common-sense reasoning is a key language model capability because it encapsulates not just specific factual knowledge but rather general language and world understanding. Measuring common-sense reasoning, therefore, is crucial for language models of different sizes and applications. One of the most widely used benchmarks for evaluating such capabilities is HellaSwag; however, in this paper, we show that it has severe construct validity issues. These issues range from basic ungrammaticality and numerous typos to misleading prompts or equally correct options. Furthermore, we show that if models ","authors_text":"Ivan P. Yamshchikov, Mattia Nee, Pavel Chizhov, Pierre-Carl Langlais","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T15:01:46Z","title":"What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07825","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":"sha256:1d423955b0168e5c456fd6056b6f3e91cbcd1bf30d0f964977852a6574f402cb","target":"record","created_at":"2026-07-05T10:47:15Z","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":"1a35559ac0ab74691d1804465c32cdbb38c95063356f8b96f325371238e4cf6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T15:01:46Z","title_canon_sha256":"95228dce548b1e43a5cca17fe1de4008a71ecb8631a421d3b0b1c2f3c5dd01a3"},"schema_version":"1.0","source":{"id":"2504.07825","kind":"arxiv","version":1}},"canonical_sha256":"e513c198a847d747d4514062bef6fb2f8763fe838132b21e1fb7ef9bd6fed424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e513c198a847d747d4514062bef6fb2f8763fe838132b21e1fb7ef9bd6fed424","first_computed_at":"2026-07-05T10:47:15.432084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:15.432084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i47F/PQYSo32Lh/TAKlp8SscgYAPpqYx4FbGexYDgn/v9Z/A2KLyx2Hc3Uj7/uaS12WzIGo64g4KTaU5IxvrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:15.432575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d423955b0168e5c456fd6056b6f3e91cbcd1bf30d0f964977852a6574f402cb","sha256:249dca773b58969863b0fa5f9e73465c237abe7aa5cf5f202ffe11ad73540cca"],"state_sha256":"b341bcfa148d8e0171eed739c1e2edbd46ae45a7382690f52f713bf603a9d7eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZ6bMGTbC95o6woPpgTPRlOjVq/T2SWXSmoMbb/NtAuy/GxvrKCBf1GcllJUoz/MqloLRupJX+sNSGoZMdg9Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:17:01.228698Z","bundle_sha256":"294c491f362aee725fffe3a7f9123aac8a283e13071554625003e4d14c9635dd"}}