{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FQ2YU5RXK2ADXSBRJMVYL7CO2J","short_pith_number":"pith:FQ2YU5RX","canonical_record":{"source":{"id":"2606.24973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T11:46:14Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"7e90ac34d5d21a447d004e3a9a5a936fea6e49c2d94e6e333a21dd76783d126a","abstract_canon_sha256":"e1b4d42ae9fecba67410fa605a19bb5215354fd3f33715e3da62a0023d195af5"},"schema_version":"1.0"},"canonical_sha256":"2c358a763756803bc8314b2b85fc4ed277b1ba99515a95b9fb67a959c8faaf76","source":{"kind":"arxiv","id":"2606.24973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24973","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24973v1","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24973","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"FQ2YU5RXK2AD","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"FQ2YU5RXK2ADXSBR","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"FQ2YU5RX","created_at":"2026-06-25T00:17:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FQ2YU5RXK2ADXSBRJMVYL7CO2J","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T11:46:14Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"7e90ac34d5d21a447d004e3a9a5a936fea6e49c2d94e6e333a21dd76783d126a","abstract_canon_sha256":"e1b4d42ae9fecba67410fa605a19bb5215354fd3f33715e3da62a0023d195af5"},"schema_version":"1.0"},"canonical_sha256":"2c358a763756803bc8314b2b85fc4ed277b1ba99515a95b9fb67a959c8faaf76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:17:47.255388Z","signature_b64":"nWA0ErUtwM1TvECXMIRtuTGx5rAA124V9VJyiZXy9Vn1q2OseBkUnCfWgpbH7dV2xdfJmjgL6WmINhoZcpYABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c358a763756803bc8314b2b85fc4ed277b1ba99515a95b9fb67a959c8faaf76","last_reissued_at":"2026-06-25T00:17:47.254972Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:17:47.254972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24973","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":"2026-06-25T00:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nFgxNbO3UZVrj+Vath3ZT7jgHZeLkDZ5GPmVp/hBKI39o0sqfbHQ5/SzgfULjaegeL6euO5OA2oxS8hol8nDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:04:47.261791Z"},"content_sha256":"3cc1a8f5b9f0c8ab47170b96e0ebaf57da2c41c0e34dcc2ffc2756f5ad4a738a","schema_version":"1.0","event_id":"sha256:3cc1a8f5b9f0c8ab47170b96e0ebaf57da2c41c0e34dcc2ffc2756f5ad4a738a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FQ2YU5RXK2ADXSBRJMVYL7CO2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Performance on a Real, Double-Marked GCSE Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kavi Samra, Malachy Fox, Paul Jung","submitted_at":"2026-06-23T11:46:14Z","abstract_excerpt":"We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken at age ~16), spanning 328 questions across five subjects and including handwritten work. We test whether off-the-shelf large language models agree with examiners as closely as the two examiners agree with each other. We find that models overwhelmingly agree well with the examiner consensus across subjects, with the top performing models agreeing more closely with examiners than examiners agree with each other. Models achieve high scores for subjective tasks like En"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24973","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/2606.24973/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":"2026-06-25T00:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/huNTWZxEz7FhvVfUvhalDhuIlbfdD9c6FyvSZLNEjF/vzItAdBZcGrM7FiSsYCod463UNA7HJrBP71dwUG2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:04:47.262527Z"},"content_sha256":"6eceebc0964138189e8f103101e0a63ca9c3dd6eb14b05dfa13a145e5e6542e6","schema_version":"1.0","event_id":"sha256:6eceebc0964138189e8f103101e0a63ca9c3dd6eb14b05dfa13a145e5e6542e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/bundle.json","state_url":"https://pith.science/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/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":"2026-08-20T14:04:47Z","links":{"resolver":"https://pith.science/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J","bundle":"https://pith.science/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/bundle.json","state":"https://pith.science/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQ2YU5RXK2ADXSBRJMVYL7CO2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FQ2YU5RXK2ADXSBRJMVYL7CO2J","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":"e1b4d42ae9fecba67410fa605a19bb5215354fd3f33715e3da62a0023d195af5","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T11:46:14Z","title_canon_sha256":"7e90ac34d5d21a447d004e3a9a5a936fea6e49c2d94e6e333a21dd76783d126a"},"schema_version":"1.0","source":{"id":"2606.24973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24973","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24973v1","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24973","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"FQ2YU5RXK2AD","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"FQ2YU5RXK2ADXSBR","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"FQ2YU5RX","created_at":"2026-06-25T00:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:6eceebc0964138189e8f103101e0a63ca9c3dd6eb14b05dfa13a145e5e6542e6","target":"graph","created_at":"2026-06-25T00:17:47Z","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/2606.24973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken at age ~16), spanning 328 questions across five subjects and including handwritten work. We test whether off-the-shelf large language models agree with examiners as closely as the two examiners agree with each other. We find that models overwhelmingly agree well with the examiner consensus across subjects, with the top performing models agreeing more closely with examiners than examiners agree with each other. Models achieve high scores for subjective tasks like En","authors_text":"Kavi Samra, Malachy Fox, Paul Jung","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T11:46:14Z","title":"LLM Performance on a Real, Double-Marked GCSE Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24973","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":"sha256:3cc1a8f5b9f0c8ab47170b96e0ebaf57da2c41c0e34dcc2ffc2756f5ad4a738a","target":"record","created_at":"2026-06-25T00:17:47Z","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":"e1b4d42ae9fecba67410fa605a19bb5215354fd3f33715e3da62a0023d195af5","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T11:46:14Z","title_canon_sha256":"7e90ac34d5d21a447d004e3a9a5a936fea6e49c2d94e6e333a21dd76783d126a"},"schema_version":"1.0","source":{"id":"2606.24973","kind":"arxiv","version":1}},"canonical_sha256":"2c358a763756803bc8314b2b85fc4ed277b1ba99515a95b9fb67a959c8faaf76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c358a763756803bc8314b2b85fc4ed277b1ba99515a95b9fb67a959c8faaf76","first_computed_at":"2026-06-25T00:17:47.254972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:17:47.254972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nWA0ErUtwM1TvECXMIRtuTGx5rAA124V9VJyiZXy9Vn1q2OseBkUnCfWgpbH7dV2xdfJmjgL6WmINhoZcpYABA==","signature_status":"signed_v1","signed_at":"2026-06-25T00:17:47.255388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cc1a8f5b9f0c8ab47170b96e0ebaf57da2c41c0e34dcc2ffc2756f5ad4a738a","sha256:6eceebc0964138189e8f103101e0a63ca9c3dd6eb14b05dfa13a145e5e6542e6"],"state_sha256":"fcb5f26109aded3ebdef1ef3d1d8857047a2b305066a32db1d1e69a953b79b66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cv7blkQL5O+FEGkj+OwkFPnfIajY+T307MpqQoi3yPLOTuP5m6sW2eYzeQTGDZ1pDq8Yfhy4B9JnIO2ff+8yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:04:47.266341Z","bundle_sha256":"2ec97a8e2f3b6d59c4be14bd0a265f331f801aa461f2871aaa7ff05b877f8b14"}}