{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLVT4AIEDM6MJ3LWRYJJ4425GT","short_pith_number":"pith:VLVT4AIE","schema_version":"1.0","canonical_sha256":"aaeb3e01041b3cc4ed768e129e735d34f2edff796e3e7e8939ce845d865270ae","source":{"kind":"arxiv","id":"2506.09813","version":2},"attestation_state":"computed","paper":{"title":"Metritocracy: Representative Metrics for Lite Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Ariel Procaccia, Benjamin Schiffer, Serena Wang, Shirley Zhang","submitted_at":"2025-06-11T14:53:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.09813","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T14:53:47Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"97409674f1c8c235914ec30c0aa763ed44f8b261a448cd7845e1401d580507ab","abstract_canon_sha256":"eae2896e0c52a4362002632346f1d2a07f4ea43df26319b238e6bb9375b2578c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:49.477267Z","signature_b64":"TRjOI7jBQOsVvcgvYB0ha07vXuviAvSdZaz3i6pP0JHcW7Rq1aMwC7yr1AVxfHIrHP2/gU7vCq17HeysbI3JDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaeb3e01041b3cc4ed768e129e735d34f2edff796e3e7e8939ce845d865270ae","last_reissued_at":"2026-07-05T11:21:49.476865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:49.476865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metritocracy: Representative Metrics for Lite Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Ariel Procaccia, Benjamin Schiffer, Serena Wang, Shirley Zhang","submitted_at":"2025-06-11T14:53:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09813","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.09813/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.09813","created_at":"2026-07-05T11:21:49.476930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09813v2","created_at":"2026-07-05T11:21:49.476930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09813","created_at":"2026-07-05T11:21:49.476930+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLVT4AIEDM6M","created_at":"2026-07-05T11:21:49.476930+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLVT4AIEDM6MJ3LW","created_at":"2026-07-05T11:21:49.476930+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLVT4AIE","created_at":"2026-07-05T11:21:49.476930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT","json":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT.json","graph_json":"https://pith.science/api/pith-number/VLVT4AIEDM6MJ3LWRYJJ4425GT/graph.json","events_json":"https://pith.science/api/pith-number/VLVT4AIEDM6MJ3LWRYJJ4425GT/events.json","paper":"https://pith.science/paper/VLVT4AIE"},"agent_actions":{"view_html":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT","download_json":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT.json","view_paper":"https://pith.science/paper/VLVT4AIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09813&json=true","fetch_graph":"https://pith.science/api/pith-number/VLVT4AIEDM6MJ3LWRYJJ4425GT/graph.json","fetch_events":"https://pith.science/api/pith-number/VLVT4AIEDM6MJ3LWRYJJ4425GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT/action/storage_attestation","attest_author":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT/action/author_attestation","sign_citation":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT/action/citation_signature","submit_replication":"https://pith.science/pith/VLVT4AIEDM6MJ3LWRYJJ4425GT/action/replication_record"}},"created_at":"2026-07-05T11:21:49.476930+00:00","updated_at":"2026-07-05T11:21:49.476930+00:00"}