{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QPWZV7Q5DAWGRAXILNREDH6LFM","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":"b0c07128daadffca5b1f3b9e011fd50a63da0c521b1a6eaabae8cc452cdc6b20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-28T21:25:37Z","title_canon_sha256":"abf16acc1ec154463ad74e7bc5e9f6811dad2730aeb16500693c39f8f23c0814"},"schema_version":"1.0","source":{"id":"2410.22368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22368","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22368v1","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22368","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"QPWZV7Q5DAWG","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"QPWZV7Q5DAWGRAXI","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"QPWZV7Q5","created_at":"2026-07-05T09:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:948d3e8bed597a271542d9b5e605a95839228593af255aadfb91480c541aa3a3","target":"graph","created_at":"2026-07-05T09:28:15Z","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/2410.22368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There exists an extremely wide array of LLM benchmarking tasks, whereas oftentimes a single number is the most actionable for decision-making, especially by non-experts. No such aggregation schema exists that is not Elo-based, which could be costly or time-consuming. Here we propose a method to aggregate performance across a general space of benchmarks, nicknamed Project \"MPG,\" dubbed Model Performance and Goodness, additionally referencing a metric widely understood to be an important yet inaccurate and crude measure of car performance. Here, we create two numbers: a \"Goodness\" number (answer","authors_text":"Dan Gruhl, Eugene Ie, Lucas Spangher, Nick Masiewicki, Peter Grabowski, Rama Parusmathi, Tianle Li, William F. Arnold, Xerxes Dotiwalla","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-28T21:25:37Z","title":"Project MPG: towards a generalized performance benchmark for LLM capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22368","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":"sha256:80d2427bec346d9901b602f42feaa878a756dc325fe96dc2539f48153976068f","target":"record","created_at":"2026-07-05T09:28:15Z","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":"b0c07128daadffca5b1f3b9e011fd50a63da0c521b1a6eaabae8cc452cdc6b20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-28T21:25:37Z","title_canon_sha256":"abf16acc1ec154463ad74e7bc5e9f6811dad2730aeb16500693c39f8f23c0814"},"schema_version":"1.0","source":{"id":"2410.22368","kind":"arxiv","version":1}},"canonical_sha256":"83ed9afe1d182c6882e85b62419fcb2b2cfd74ef36ef571e06b117796ea12daf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83ed9afe1d182c6882e85b62419fcb2b2cfd74ef36ef571e06b117796ea12daf","first_computed_at":"2026-07-05T09:28:15.504673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:15.504673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aCP+7W5DutzmbH63Di/RC+YjMf/HPgKGUWRYWZt5cM5DcqZt1vuw45X3fLuUkTJqIl1y/NDVBOYdKpK++oTKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:15.505153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d2427bec346d9901b602f42feaa878a756dc325fe96dc2539f48153976068f","sha256:948d3e8bed597a271542d9b5e605a95839228593af255aadfb91480c541aa3a3"],"state_sha256":"df6ed03f3b25f791a71f2b98da0cb4b05a1b9c4cd942de079b8fe69721991b81"}