{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JZ4TUHGAOBXFEERZACOV42RQJU","short_pith_number":"pith:JZ4TUHGA","canonical_record":{"source":{"id":"1811.08186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-20T11:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"a1c60c078eaaf398b8a311d0733a7e2d4822aae7f2bfa8cf2875bf3d8b68683f","abstract_canon_sha256":"10a7e67799db22613f67c36d453c094988245d7983ae97a6300012509f0ba926"},"schema_version":"1.0"},"canonical_sha256":"4e793a1cc0706e521239009d5e6a304d35314b4257155e7d12f8765b5af2fabc","source":{"kind":"arxiv","id":"1811.08186","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08186","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08186v2","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08186","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"JZ4TUHGAOBXF","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"JZ4TUHGAOBXFEERZ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"JZ4TUHGA","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JZ4TUHGAOBXFEERZACOV42RQJU","target":"record","payload":{"canonical_record":{"source":{"id":"1811.08186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-20T11:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"a1c60c078eaaf398b8a311d0733a7e2d4822aae7f2bfa8cf2875bf3d8b68683f","abstract_canon_sha256":"10a7e67799db22613f67c36d453c094988245d7983ae97a6300012509f0ba926"},"schema_version":"1.0"},"canonical_sha256":"4e793a1cc0706e521239009d5e6a304d35314b4257155e7d12f8765b5af2fabc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:40.874710Z","signature_b64":"jpqkc5ch7QlhhnrAxJ6WVXTfkei/IVznIyrvlTZdZfehd1J6tA7C2NXqStjLJTC5haruZyVnFDqTqH33DajEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e793a1cc0706e521239009d5e6a304d35314b4257155e7d12f8765b5af2fabc","last_reissued_at":"2026-05-17T23:50:40.874277Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:40.874277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.08186","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Ww6OGCybWhazrllJMsTejO9qPAs7DCkmPQjtVCxoRQfdavsO/4HZUBjcTZuKVZ0UWjncBdvvJcHLWpQApXqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:00:57.690284Z"},"content_sha256":"daefd441b0958d73a6f82c1d5464a1697bfe65d0c5b5e627669f913c64f2737f","schema_version":"1.0","event_id":"sha256:daefd441b0958d73a6f82c1d5464a1697bfe65d0c5b5e627669f913c64f2737f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JZ4TUHGAOBXFEERZACOV42RQJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysing Results from AI Benchmarks: Key Indicators and How to Obtain Them","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fernando Mart\\'inez-Plumed, Jos\\'e Hern\\'andez-Orallo","submitted_at":"2018-11-20T11:26:36Z","abstract_excerpt":"Item response theory (IRT) can be applied to the analysis of the evaluation of results from AI benchmarks. The two-parameter IRT model provides two indicators (difficulty and discrimination) on the side of the item (or AI problem) while only one indicator (ability) on the side of the respondent (or AI agent). In this paper we analyse how to make this set of indicators dual, by adding a fourth indicator, generality, on the side of the respondent. Generality is meant to be dual to discrimination, and it is based on difficulty. Namely, generality is defined as a new metric that evaluates whether "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08186","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/5EFA1fipUYkhVHw4MN7sdCaDaXbeMpzflq082l3yTwqYZmR4GJWwXwNBWaiZ/djOtKk5G+NB/BZclA23NX0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:00:57.690794Z"},"content_sha256":"e2cd09e67c8ce48366784f1c3deed98a7448580a6aad4155972850c805d78216","schema_version":"1.0","event_id":"sha256:e2cd09e67c8ce48366784f1c3deed98a7448580a6aad4155972850c805d78216"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JZ4TUHGAOBXFEERZACOV42RQJU/bundle.json","state_url":"https://pith.science/pith/JZ4TUHGAOBXFEERZACOV42RQJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JZ4TUHGAOBXFEERZACOV42RQJU/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":"2026-06-04T22:00:57Z","links":{"resolver":"https://pith.science/pith/JZ4TUHGAOBXFEERZACOV42RQJU","bundle":"https://pith.science/pith/JZ4TUHGAOBXFEERZACOV42RQJU/bundle.json","state":"https://pith.science/pith/JZ4TUHGAOBXFEERZACOV42RQJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JZ4TUHGAOBXFEERZACOV42RQJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JZ4TUHGAOBXFEERZACOV42RQJU","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":"10a7e67799db22613f67c36d453c094988245d7983ae97a6300012509f0ba926","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-20T11:26:36Z","title_canon_sha256":"a1c60c078eaaf398b8a311d0733a7e2d4822aae7f2bfa8cf2875bf3d8b68683f"},"schema_version":"1.0","source":{"id":"1811.08186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08186","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08186v2","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08186","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"JZ4TUHGAOBXF","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"JZ4TUHGAOBXFEERZ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"JZ4TUHGA","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:e2cd09e67c8ce48366784f1c3deed98a7448580a6aad4155972850c805d78216","target":"graph","created_at":"2026-05-17T23:50:40Z","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"},"paper":{"abstract_excerpt":"Item response theory (IRT) can be applied to the analysis of the evaluation of results from AI benchmarks. The two-parameter IRT model provides two indicators (difficulty and discrimination) on the side of the item (or AI problem) while only one indicator (ability) on the side of the respondent (or AI agent). In this paper we analyse how to make this set of indicators dual, by adding a fourth indicator, generality, on the side of the respondent. Generality is meant to be dual to discrimination, and it is based on difficulty. Namely, generality is defined as a new metric that evaluates whether ","authors_text":"Fernando Mart\\'inez-Plumed, Jos\\'e Hern\\'andez-Orallo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-20T11:26:36Z","title":"Analysing Results from AI Benchmarks: Key Indicators and How to Obtain Them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08186","kind":"arxiv","version":2},"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:daefd441b0958d73a6f82c1d5464a1697bfe65d0c5b5e627669f913c64f2737f","target":"record","created_at":"2026-05-17T23:50:40Z","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":"10a7e67799db22613f67c36d453c094988245d7983ae97a6300012509f0ba926","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-20T11:26:36Z","title_canon_sha256":"a1c60c078eaaf398b8a311d0733a7e2d4822aae7f2bfa8cf2875bf3d8b68683f"},"schema_version":"1.0","source":{"id":"1811.08186","kind":"arxiv","version":2}},"canonical_sha256":"4e793a1cc0706e521239009d5e6a304d35314b4257155e7d12f8765b5af2fabc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e793a1cc0706e521239009d5e6a304d35314b4257155e7d12f8765b5af2fabc","first_computed_at":"2026-05-17T23:50:40.874277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:40.874277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jpqkc5ch7QlhhnrAxJ6WVXTfkei/IVznIyrvlTZdZfehd1J6tA7C2NXqStjLJTC5haruZyVnFDqTqH33DajEBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:40.874710Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.08186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:daefd441b0958d73a6f82c1d5464a1697bfe65d0c5b5e627669f913c64f2737f","sha256:e2cd09e67c8ce48366784f1c3deed98a7448580a6aad4155972850c805d78216"],"state_sha256":"0552e3d43fe52d30443f5debb349ce9b4c2134f53c0a2bc7a2b9694253a298ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsXLYOF9ixVElqmt9f7sQeiguEyDc6xQzskqTODq07Q5OuxLqmHV9jQZeikSaw0Wwb9XD7FStUnzphELMWkhDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T22:00:57.692773Z","bundle_sha256":"e3ce55dafde2f321295ccba9e8e728599a5e70ff9f6f0d02f96873f9c3d65e25"}}