{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HKF426WYO5OEZTYRDBHFWL36NH","short_pith_number":"pith:HKF426WY","canonical_record":{"source":{"id":"2506.07962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:37:18Z","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"title_canon_sha256":"bac9cf39bac4ff89a2a62cb9fefc376d9669861d5da8ac2a279fb35ba83b5058","abstract_canon_sha256":"d5f0d00087ebe40d797312534e640a75869f468cb000cec4c320a3a2a2855483"},"schema_version":"1.0"},"canonical_sha256":"3a8bcd7ad8775c4ccf11184e5b2f7e69d5f73846cfff495349a7e7d97023ddbf","source":{"kind":"arxiv","id":"2506.07962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07962","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07962v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07962","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"HKF426WYO5OE","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"HKF426WYO5OEZTYR","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"HKF426WY","created_at":"2026-07-05T11:18:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HKF426WYO5OEZTYRDBHFWL36NH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:37:18Z","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"title_canon_sha256":"bac9cf39bac4ff89a2a62cb9fefc376d9669861d5da8ac2a279fb35ba83b5058","abstract_canon_sha256":"d5f0d00087ebe40d797312534e640a75869f468cb000cec4c320a3a2a2855483"},"schema_version":"1.0"},"canonical_sha256":"3a8bcd7ad8775c4ccf11184e5b2f7e69d5f73846cfff495349a7e7d97023ddbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:36.158399Z","signature_b64":"zrJLdihQWB5ON+ljfh0+V5AWB9qXjJDNVpM4ZxatJ+okTNCzAeprncGl1kLiz99GalrSc1Bylygxl+sxQXXFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a8bcd7ad8775c4ccf11184e5b2f7e69d5f73846cfff495349a7e7d97023ddbf","last_reissued_at":"2026-07-05T11:18:36.157875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:36.157875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07962","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":"2026-07-05T11:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWTavkNDhxkXRraItGwoZmwvuGeu0BG4zCP2EXSfpxQOFKN7TRCIJlBd9aGSRYoVwGJO4sSdE+FEtvkUFhidBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:11:20.268863Z"},"content_sha256":"1b2a2cab04a3ab839a0c0227eb441d3f8f130f02b80723a69ce5e06c5bbee1e6","schema_version":"1.0","event_id":"sha256:1b2a2cab04a3ab839a0c0227eb441d3f8f130f02b80723a69ce5e06c5bbee1e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HKF426WYO5OEZTYRDBHFWL36NH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correlated Errors in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","stat.ML"],"primary_cat":"cs.CL","authors_text":"Avi Garg, Elliot Kim, Kenny Peng, Nikhil Garg","submitted_at":"2025-06-09T17:37:18Z","abstract_excerpt":"Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical evaluation on over 350 LLMs overall, using two popular leaderboards and a resume-screening task. We find substantial correlation in model errors -- on one leaderboard dataset, models agree 60% of the time when both models err. We identify factors driving model correlation, including shared architectures and providers. Crucially, however, larger and more accurate models have highl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07962","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/2506.07962/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":"2026-07-05T11:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJULt7l4k6d32BFujfP+kdlq6bO7RxLDm9cafVi5ZQnFTrTtD6G3r348+K0tjpKZHnGmZGR27FcakV2WZTP6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:11:20.269777Z"},"content_sha256":"57ab4739855eebd81471f342fdb9bfaa01de2602fcd9b9718ef0136757b5283c","schema_version":"1.0","event_id":"sha256:57ab4739855eebd81471f342fdb9bfaa01de2602fcd9b9718ef0136757b5283c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKF426WYO5OEZTYRDBHFWL36NH/bundle.json","state_url":"https://pith.science/pith/HKF426WYO5OEZTYRDBHFWL36NH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKF426WYO5OEZTYRDBHFWL36NH/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":"2026-08-05T02:11:20Z","links":{"resolver":"https://pith.science/pith/HKF426WYO5OEZTYRDBHFWL36NH","bundle":"https://pith.science/pith/HKF426WYO5OEZTYRDBHFWL36NH/bundle.json","state":"https://pith.science/pith/HKF426WYO5OEZTYRDBHFWL36NH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKF426WYO5OEZTYRDBHFWL36NH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HKF426WYO5OEZTYRDBHFWL36NH","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":"d5f0d00087ebe40d797312534e640a75869f468cb000cec4c320a3a2a2855483","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:37:18Z","title_canon_sha256":"bac9cf39bac4ff89a2a62cb9fefc376d9669861d5da8ac2a279fb35ba83b5058"},"schema_version":"1.0","source":{"id":"2506.07962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07962","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07962v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07962","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"HKF426WYO5OE","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"HKF426WYO5OEZTYR","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"HKF426WY","created_at":"2026-07-05T11:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:57ab4739855eebd81471f342fdb9bfaa01de2602fcd9b9718ef0136757b5283c","target":"graph","created_at":"2026-07-05T11:18:36Z","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/2506.07962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical evaluation on over 350 LLMs overall, using two popular leaderboards and a resume-screening task. We find substantial correlation in model errors -- on one leaderboard dataset, models agree 60% of the time when both models err. We identify factors driving model correlation, including shared architectures and providers. Crucially, however, larger and more accurate models have highl","authors_text":"Avi Garg, Elliot Kim, Kenny Peng, Nikhil Garg","cross_cats":["cs.AI","cs.CY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:37:18Z","title":"Correlated Errors in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07962","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":"sha256:1b2a2cab04a3ab839a0c0227eb441d3f8f130f02b80723a69ce5e06c5bbee1e6","target":"record","created_at":"2026-07-05T11:18:36Z","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":"d5f0d00087ebe40d797312534e640a75869f468cb000cec4c320a3a2a2855483","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:37:18Z","title_canon_sha256":"bac9cf39bac4ff89a2a62cb9fefc376d9669861d5da8ac2a279fb35ba83b5058"},"schema_version":"1.0","source":{"id":"2506.07962","kind":"arxiv","version":1}},"canonical_sha256":"3a8bcd7ad8775c4ccf11184e5b2f7e69d5f73846cfff495349a7e7d97023ddbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a8bcd7ad8775c4ccf11184e5b2f7e69d5f73846cfff495349a7e7d97023ddbf","first_computed_at":"2026-07-05T11:18:36.157875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:36.157875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zrJLdihQWB5ON+ljfh0+V5AWB9qXjJDNVpM4ZxatJ+okTNCzAeprncGl1kLiz99GalrSc1Bylygxl+sxQXXFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:36.158399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b2a2cab04a3ab839a0c0227eb441d3f8f130f02b80723a69ce5e06c5bbee1e6","sha256:57ab4739855eebd81471f342fdb9bfaa01de2602fcd9b9718ef0136757b5283c"],"state_sha256":"11a84272205961a335da34b0f0b0abe665aeec186bd292ade287f2abd2fd0b47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4tpEGqTbVtVtLqz3ctgX9/B6ivfWNNXvS6GbNnolKwAonYHthczAdNCui6Jf7NS+8QquUE16XpYVhpGn1yYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:11:20.276802Z","bundle_sha256":"2a31dd81db3aec89e4235d1c75a2301cf0427a9d9d543b6d2fdaec2bb3863f67"}}