{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TFQHPDUM76Y32Y4EXB3XT6KJOX","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":"7ed04cab4757eb149bc8687ec89c816048a6054be2b7a557d44fd789a248885a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:03:19Z","title_canon_sha256":"787381706b59b47d8d053798112de1b447f80aedba565208920392529fa3ecec"},"schema_version":"1.0","source":{"id":"2606.07726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07726","created_at":"2026-06-09T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07726v1","created_at":"2026-06-09T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07726","created_at":"2026-06-09T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"TFQHPDUM76Y3","created_at":"2026-06-09T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"TFQHPDUM76Y32Y4E","created_at":"2026-06-09T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"TFQHPDUM","created_at":"2026-06-09T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:13830d37dc8c06fc3043b564789847be91d8753a3e635a8a9a727b9196080422","target":"graph","created_at":"2026-06-09T01:04:50Z","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/2606.07726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chahine Nejma, Fanny Yang, Florian E. Dorner, Tobias Wegel, Zifan Lyu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:03:19Z","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07726","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":"sha256:4c72335b9b9d186b5e4b152d2fd8da030b73e6f5184240e333075f1e9d19683d","target":"record","created_at":"2026-06-09T01:04:50Z","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":"7ed04cab4757eb149bc8687ec89c816048a6054be2b7a557d44fd789a248885a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:03:19Z","title_canon_sha256":"787381706b59b47d8d053798112de1b447f80aedba565208920392529fa3ecec"},"schema_version":"1.0","source":{"id":"2606.07726","kind":"arxiv","version":1}},"canonical_sha256":"9960778e8cffb1bd6384b87779f94975c10d50de0d627c1130ec6c008c47bfb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9960778e8cffb1bd6384b87779f94975c10d50de0d627c1130ec6c008c47bfb2","first_computed_at":"2026-06-09T01:04:50.478526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:50.478526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2z/LSI8iMNsiQfF4swJUdXycFX612TZ/vBfL9dg8cpsbdceSJfrt76pFtbd5naEI27g1TPZWa8wflkx99K4JBw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:50.478940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c72335b9b9d186b5e4b152d2fd8da030b73e6f5184240e333075f1e9d19683d","sha256:13830d37dc8c06fc3043b564789847be91d8753a3e635a8a9a727b9196080422"],"state_sha256":"123ef0f07549aa71010390946b148dce6d2ad9c352811265443e016307ee55f0"}