{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3EQ7MLOC4RV3MQCFBAP42EF7CX","short_pith_number":"pith:3EQ7MLOC","canonical_record":{"source":{"id":"2607.15190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T16:44:40Z","cross_cats_sorted":[],"title_canon_sha256":"655e65df71376c05cc6f46cf05972907e55f59e8b12dcfdbc89d18d67f0d1131","abstract_canon_sha256":"3c54274aded803830a79cab6e31844fb7ca989903c8b98530535dba3aff104c6"},"schema_version":"1.0"},"canonical_sha256":"d921f62dc2e46bb64045081fcd10bf15ff3ca6a819c0474c285369775ca6efa7","source":{"kind":"arxiv","id":"2607.15190","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15190","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15190v1","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15190","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"3EQ7MLOC4RV3","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"3EQ7MLOC4RV3MQCF","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"3EQ7MLOC","created_at":"2026-07-17T01:22:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3EQ7MLOC4RV3MQCFBAP42EF7CX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T16:44:40Z","cross_cats_sorted":[],"title_canon_sha256":"655e65df71376c05cc6f46cf05972907e55f59e8b12dcfdbc89d18d67f0d1131","abstract_canon_sha256":"3c54274aded803830a79cab6e31844fb7ca989903c8b98530535dba3aff104c6"},"schema_version":"1.0"},"canonical_sha256":"d921f62dc2e46bb64045081fcd10bf15ff3ca6a819c0474c285369775ca6efa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:13.605794Z","signature_b64":"vGJIwGOKnOlHPHU3VQ+bs6gzgugYuf9CDaA3SSpE/TqhoyM/a4qUdyRylmAqpPZGtQmhCdNRDq1WXWRnl0IJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d921f62dc2e46bb64045081fcd10bf15ff3ca6a819c0474c285369775ca6efa7","last_reissued_at":"2026-07-17T01:22:13.604946Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:13.604946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15190","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":"2026-07-17T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6U3QbJO8X/0r0v64BO3WnbzL2cj2mESwqkH50CSDnS84ocHZIRHEWn0L4rnpk3iUxXcJxjQeoiVGkxTW/WIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:59:19.196795Z"},"content_sha256":"89381183340f6b492510eac0d7bc6b44da669d24bd48cbc070ad095ce082e25e","schema_version":"1.0","event_id":"sha256:89381183340f6b492510eac0d7bc6b44da669d24bd48cbc070ad095ce082e25e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3EQ7MLOC4RV3MQCFBAP42EF7CX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can We Trust Item Response Theory for AI Evaluation?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Han Jiang, Jinwen Luo, Sunbeom Kwon, Susu Zhang, Ziang Xiao","submitted_at":"2026-07-16T16:44:40Z","abstract_excerpt":"AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for which standard IRT estimation tools were originally developed: benchmarks typically involve fewer evaluated models, far more items, and capability distributions that may be skewed, clustered, or multimodal. We examine how these regime mismatches challenge the reliability of IRT modeling for AI evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15190","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/2607.15190/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":"2026-07-17T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlzqGubDKVr/d4xfbtyqIphqsRNnHZ+zBxX7Mz9W3MmCJQ+twyskrk34ahWSl2ozUq3Fy8ESOnGctWaWoViUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:59:19.197760Z"},"content_sha256":"b6d0c1dc6138c090b5203b806219160f815491af858999cf4f91c6af1f5b6672","schema_version":"1.0","event_id":"sha256:b6d0c1dc6138c090b5203b806219160f815491af858999cf4f91c6af1f5b6672"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/bundle.json","state_url":"https://pith.science/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/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":"2026-08-05T02:59:19Z","links":{"resolver":"https://pith.science/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX","bundle":"https://pith.science/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/bundle.json","state":"https://pith.science/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EQ7MLOC4RV3MQCFBAP42EF7CX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3EQ7MLOC4RV3MQCFBAP42EF7CX","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":"3c54274aded803830a79cab6e31844fb7ca989903c8b98530535dba3aff104c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T16:44:40Z","title_canon_sha256":"655e65df71376c05cc6f46cf05972907e55f59e8b12dcfdbc89d18d67f0d1131"},"schema_version":"1.0","source":{"id":"2607.15190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15190","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15190v1","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15190","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"3EQ7MLOC4RV3","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"3EQ7MLOC4RV3MQCF","created_at":"2026-07-17T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"3EQ7MLOC","created_at":"2026-07-17T01:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:b6d0c1dc6138c090b5203b806219160f815491af858999cf4f91c6af1f5b6672","target":"graph","created_at":"2026-07-17T01:22:13Z","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/2607.15190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for which standard IRT estimation tools were originally developed: benchmarks typically involve fewer evaluated models, far more items, and capability distributions that may be skewed, clustered, or multimodal. We examine how these regime mismatches challenge the reliability of IRT modeling for AI evalua","authors_text":"Han Jiang, Jinwen Luo, Sunbeom Kwon, Susu Zhang, Ziang Xiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T16:44:40Z","title":"Can We Trust Item Response Theory for AI Evaluation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15190","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":"sha256:89381183340f6b492510eac0d7bc6b44da669d24bd48cbc070ad095ce082e25e","target":"record","created_at":"2026-07-17T01:22:13Z","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":"3c54274aded803830a79cab6e31844fb7ca989903c8b98530535dba3aff104c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T16:44:40Z","title_canon_sha256":"655e65df71376c05cc6f46cf05972907e55f59e8b12dcfdbc89d18d67f0d1131"},"schema_version":"1.0","source":{"id":"2607.15190","kind":"arxiv","version":1}},"canonical_sha256":"d921f62dc2e46bb64045081fcd10bf15ff3ca6a819c0474c285369775ca6efa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d921f62dc2e46bb64045081fcd10bf15ff3ca6a819c0474c285369775ca6efa7","first_computed_at":"2026-07-17T01:22:13.604946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:13.604946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vGJIwGOKnOlHPHU3VQ+bs6gzgugYuf9CDaA3SSpE/TqhoyM/a4qUdyRylmAqpPZGtQmhCdNRDq1WXWRnl0IJCg==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:13.605794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89381183340f6b492510eac0d7bc6b44da669d24bd48cbc070ad095ce082e25e","sha256:b6d0c1dc6138c090b5203b806219160f815491af858999cf4f91c6af1f5b6672"],"state_sha256":"edda2442c41d162d8e89c6d4b43fed3c0b94e707f54fa2449651d3b53de31727"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMR0g8HYTzEOYtzmdV6RJk+xJm0aZ/jdZQwONC1ZhxtIy7SG3+XvjwDaVBJICLeWhadD9pLv3wi45CHgL55gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:59:19.205254Z","bundle_sha256":"1049cb9f8f042cb499d3a70fe7dea241f0ef88a9aa8dbd3f5b74ab77a21d224e"}}