{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLVT4AIEDM6MJ3LWRYJJ4425GT","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":"eae2896e0c52a4362002632346f1d2a07f4ea43df26319b238e6bb9375b2578c","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T14:53:47Z","title_canon_sha256":"97409674f1c8c235914ec30c0aa763ed44f8b261a448cd7845e1401d580507ab"},"schema_version":"1.0","source":{"id":"2506.09813","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09813","created_at":"2026-07-05T11:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09813v2","created_at":"2026-07-05T11:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09813","created_at":"2026-07-05T11:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"VLVT4AIEDM6M","created_at":"2026-07-05T11:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"VLVT4AIEDM6MJ3LW","created_at":"2026-07-05T11:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"VLVT4AIE","created_at":"2026-07-05T11:21:49Z"}],"graph_snapshots":[{"event_id":"sha256:79f48b0f09c0561b282173a9c9b2a450f07750e06db6733be7432a89b9fe82ca","target":"graph","created_at":"2026-07-05T11:21:49Z","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/2506.09813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common problem in LLM evaluation is how to choose a subset of metrics from a full suite of possible metrics. Subset selection is usually done for efficiency or interpretability reasons, and the goal is often to select a ``representative'' subset of metrics. However, ``representative'' is rarely clearly defined. In this work, we use ideas from social choice theory to formalize two notions of representation for the selection of a subset of evaluation metrics. We first introduce positional representation, which guarantees every alternative is sufficiently represented at every position cutoff. W","authors_text":"Ariel Procaccia, Benjamin Schiffer, Serena Wang, Shirley Zhang","cross_cats":["cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T14:53:47Z","title":"Metritocracy: Representative Metrics for Lite Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09813","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":"sha256:8ce86e8e0ff41d37ce40c4c492ddeeba48227a9c2b22e8bc848fbac763d23580","target":"record","created_at":"2026-07-05T11:21:49Z","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":"eae2896e0c52a4362002632346f1d2a07f4ea43df26319b238e6bb9375b2578c","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T14:53:47Z","title_canon_sha256":"97409674f1c8c235914ec30c0aa763ed44f8b261a448cd7845e1401d580507ab"},"schema_version":"1.0","source":{"id":"2506.09813","kind":"arxiv","version":2}},"canonical_sha256":"aaeb3e01041b3cc4ed768e129e735d34f2edff796e3e7e8939ce845d865270ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaeb3e01041b3cc4ed768e129e735d34f2edff796e3e7e8939ce845d865270ae","first_computed_at":"2026-07-05T11:21:49.476865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:49.476865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TRjOI7jBQOsVvcgvYB0ha07vXuviAvSdZaz3i6pP0JHcW7Rq1aMwC7yr1AVxfHIrHP2/gU7vCq17HeysbI3JDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:49.477267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09813","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce86e8e0ff41d37ce40c4c492ddeeba48227a9c2b22e8bc848fbac763d23580","sha256:79f48b0f09c0561b282173a9c9b2a450f07750e06db6733be7432a89b9fe82ca"],"state_sha256":"9cccf10f8a367743843e4eaecbba6ce3023294fab16bd5371cd2e64089ad7a35"}