{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3O3XWA7WOTLZZDWQLMMDZWSH6C","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":"e70628ba1514a1bb00cead7d2d5384f41a280ac59d13d666af68189d522f01e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T14:17:03Z","title_canon_sha256":"5ae67957ac56b7ed982f2f6de62ca772ff5ff81317a2777295d6cf581366457e"},"schema_version":"1.0","source":{"id":"2607.08522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08522","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08522v1","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08522","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"3O3XWA7WOTLZ","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"3O3XWA7WOTLZZDWQ","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"3O3XWA7W","created_at":"2026-07-10T01:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:fbd985be14e8db2601fd91b236c0324609ac7e3484d20142dbcfed3c758fd896","target":"graph","created_at":"2026-07-10T01:19:52Z","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/2607.08522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The inherent rigidity of fixed-size benchmarks makes them an inefficient tool for model evaluation. Diverse evaluation objectives, including model ranking, model selection and testing throughout development, demand varying levels of statistical power. The mismatch between fixed sample sizes and these diverse needs results in either excessive computational cost or compromised reliability - a critical concern for model evaluation. To overcome these limitations, we call for adoption of sequential testing in our field. We provide an adaptive evaluation framework, that provides a principled way to ","authors_text":"Hadar Mulian, Kristjan Greenewald, Leshem Choshen, Michal Shmueli-Scheuer, Ofir Arviv, Yotam Perlitz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T14:17:03Z","title":"Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08522","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":"sha256:7e69f27f73fa820f676b2f8b37d792c076d310461c07ed8b8c8b2d8947144069","target":"record","created_at":"2026-07-10T01:19:52Z","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":"e70628ba1514a1bb00cead7d2d5384f41a280ac59d13d666af68189d522f01e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T14:17:03Z","title_canon_sha256":"5ae67957ac56b7ed982f2f6de62ca772ff5ff81317a2777295d6cf581366457e"},"schema_version":"1.0","source":{"id":"2607.08522","kind":"arxiv","version":1}},"canonical_sha256":"dbb77b03f674d79c8ed05b183cda47f085111f9e204da231e59310dc9f4ceb23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbb77b03f674d79c8ed05b183cda47f085111f9e204da231e59310dc9f4ceb23","first_computed_at":"2026-07-10T01:19:52.784026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:52.784026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"47RT9BNpnrUUuiv1WMhU0FDcVZsFdVLur+Jygig64wr8obGyNolSmjUFCpYnc2qoX6jhXNibPxD7Z5DLhwb+Dw==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:52.784471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e69f27f73fa820f676b2f8b37d792c076d310461c07ed8b8c8b2d8947144069","sha256:fbd985be14e8db2601fd91b236c0324609ac7e3484d20142dbcfed3c758fd896"],"state_sha256":"52f2ee4267ec960ebc5373c6edb902afe7fce85234426602927b3da49e12052f"}