{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TFQHPDUM76Y32Y4EXB3XT6KJOX","short_pith_number":"pith:TFQHPDUM","schema_version":"1.0","canonical_sha256":"9960778e8cffb1bd6384b87779f94975c10d50de0d627c1130ec6c008c47bfb2","source":{"kind":"arxiv","id":"2606.07726","version":1},"attestation_state":"computed","paper":{"title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chahine Nejma, Fanny Yang, Florian E. Dorner, Tobias Wegel, Zifan Lyu","submitted_at":"2026-06-05T17:03:19Z","abstract_excerpt":"Large Language Models are typically benchmarked by evaluating every model on every test query. For practitioners seeking the best model to deploy, this is often wasteful: if a model clearly performs worse than others, there is no need to precisely estimate its performance. Best-arm identification algorithms can be naturally applied to drastically reduce costs by adaptively allocating evaluation budget. Further, language models often respond similarly to the same prompt-a property previous work has tried to leverage with mixed success. We propose Synchronized Successive Rejects (SySRs), augment"},"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":"2606.07726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:03:19Z","cross_cats_sorted":[],"title_canon_sha256":"787381706b59b47d8d053798112de1b447f80aedba565208920392529fa3ecec","abstract_canon_sha256":"7ed04cab4757eb149bc8687ec89c816048a6054be2b7a557d44fd789a248885a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:50.478940Z","signature_b64":"2z/LSI8iMNsiQfF4swJUdXycFX612TZ/vBfL9dg8cpsbdceSJfrt76pFtbd5naEI27g1TPZWa8wflkx99K4JBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9960778e8cffb1bd6384b87779f94975c10d50de0d627c1130ec6c008c47bfb2","last_reissued_at":"2026-06-09T01:04:50.478526Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:50.478526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chahine Nejma, Fanny Yang, Florian E. Dorner, Tobias Wegel, Zifan Lyu","submitted_at":"2026-06-05T17:03:19Z","abstract_excerpt":"Large Language Models are typically benchmarked by evaluating every model on every test query. For practitioners seeking the best model to deploy, this is often wasteful: if a model clearly performs worse than others, there is no need to precisely estimate its performance. Best-arm identification algorithms can be naturally applied to drastically reduce costs by adaptively allocating evaluation budget. Further, language models often respond similarly to the same prompt-a property previous work has tried to leverage with mixed success. We propose Synchronized Successive Rejects (SySRs), augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07726","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/2606.07726/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":"2606.07726","created_at":"2026-06-09T01:04:50.478591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07726v1","created_at":"2026-06-09T01:04:50.478591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07726","created_at":"2026-06-09T01:04:50.478591+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFQHPDUM76Y3","created_at":"2026-06-09T01:04:50.478591+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFQHPDUM76Y32Y4E","created_at":"2026-06-09T01:04:50.478591+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFQHPDUM","created_at":"2026-06-09T01:04:50.478591+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/TFQHPDUM76Y32Y4EXB3XT6KJOX","json":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX.json","graph_json":"https://pith.science/api/pith-number/TFQHPDUM76Y32Y4EXB3XT6KJOX/graph.json","events_json":"https://pith.science/api/pith-number/TFQHPDUM76Y32Y4EXB3XT6KJOX/events.json","paper":"https://pith.science/paper/TFQHPDUM"},"agent_actions":{"view_html":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX","download_json":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX.json","view_paper":"https://pith.science/paper/TFQHPDUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07726&json=true","fetch_graph":"https://pith.science/api/pith-number/TFQHPDUM76Y32Y4EXB3XT6KJOX/graph.json","fetch_events":"https://pith.science/api/pith-number/TFQHPDUM76Y32Y4EXB3XT6KJOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX/action/storage_attestation","attest_author":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX/action/author_attestation","sign_citation":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX/action/citation_signature","submit_replication":"https://pith.science/pith/TFQHPDUM76Y32Y4EXB3XT6KJOX/action/replication_record"}},"created_at":"2026-06-09T01:04:50.478591+00:00","updated_at":"2026-06-09T01:04:50.478591+00:00"}