{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2KRP3FZ4EVHSQP4UWVBGOBO3EN","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":"766a9508f345d42197aa179c8331b7ee57e5a35cdd150c29a32d0c0c31d1e429","cross_cats_sorted":["cs.AI","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T21:21:46Z","title_canon_sha256":"1ebba657d20336328e03ac1750990fee3a6222bc21cbab5ea2e15a4610567dcd"},"schema_version":"1.0","source":{"id":"2501.17200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17200","created_at":"2026-07-05T10:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17200v1","created_at":"2026-07-05T10:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17200","created_at":"2026-07-05T10:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"2KRP3FZ4EVHS","created_at":"2026-07-05T10:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"2KRP3FZ4EVHSQP4U","created_at":"2026-07-05T10:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"2KRP3FZ4","created_at":"2026-07-05T10:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:6d65bf0603f972c8613aa8571b0bd13ec69c52a388f6d2cd415057a775963b63","target":"graph","created_at":"2026-07-05T10:06:49Z","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/2501.17200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of large language models (LLMs) has necessitated the creation of benchmarks to evaluate their performance. These benchmarks resemble human tests and surveys, as they consist of sets of questions designed to measure emergent properties in the cognitive behavior of these systems. However, unlike the well-defined traits and abilities studied in social sciences, the properties measured by these benchmarks are often vaguer and less rigorously defined. The most prominent benchmarks are often grouped into leaderboards for convenience, aggregating performance metrics and enabling","authors_text":"Denis Federiakin","cross_cats":["cs.AI","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T21:21:46Z","title":"Improving LLM Leaderboards with Psychometrical Methodology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17200","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:da108e21758dd2be049e5a44b4c63998100738951c861c2537327b464d2d4fcc","target":"record","created_at":"2026-07-05T10:06:49Z","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":"766a9508f345d42197aa179c8331b7ee57e5a35cdd150c29a32d0c0c31d1e429","cross_cats_sorted":["cs.AI","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T21:21:46Z","title_canon_sha256":"1ebba657d20336328e03ac1750990fee3a6222bc21cbab5ea2e15a4610567dcd"},"schema_version":"1.0","source":{"id":"2501.17200","kind":"arxiv","version":1}},"canonical_sha256":"d2a2fd973c254f283f94b5426705db236052ab11c69e1418e7372a14b50da0e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a2fd973c254f283f94b5426705db236052ab11c69e1418e7372a14b50da0e0","first_computed_at":"2026-07-05T10:06:49.115491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:49.115491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ryCq9jTWOYKeLOTqaYJw7oYrrXF6q0p6mK8bKU9Ke5+L4MciXGa3/N1GTPJLXIPkAH366yh1JlZ0rYVqkdXgAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:49.115993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da108e21758dd2be049e5a44b4c63998100738951c861c2537327b464d2d4fcc","sha256:6d65bf0603f972c8613aa8571b0bd13ec69c52a388f6d2cd415057a775963b63"],"state_sha256":"4488bc71dd32dda1b302980546ebfd090e73af7289df8118bb73b2779f1f5b7d"}