{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YOK4N5EJZFEF4NBH3Y7BKJ7GYV","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":"16878597879e2f0ae3f3f9846e791c2219399bca9b92899ca2531b1f254d7094","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T15:09:08Z","title_canon_sha256":"9ec14e8d139f2c00f61b97d6d097c12c6a734053fa485bd44ebc1dccd9114922"},"schema_version":"1.0","source":{"id":"2501.17195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17195","created_at":"2026-07-05T10:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17195v1","created_at":"2026-07-05T10:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17195","created_at":"2026-07-05T10:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"YOK4N5EJZFEF","created_at":"2026-07-05T10:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"YOK4N5EJZFEF4NBH","created_at":"2026-07-05T10:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"YOK4N5EJ","created_at":"2026-07-05T10:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:6146841e2837df84dee0ca62dbd24bfe2a4a1ae0bb143f261f56fc2dcaf327c1","target":"graph","created_at":"2026-07-05T10:06:48Z","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/2501.17195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Atla Selene Mini, a state-of-the-art small language model-as-a-judge (SLMJ). Selene Mini is a general-purpose evaluator that outperforms the best SLMJs and GPT-4o-mini on overall performance across 11 out-of-distribution benchmarks, spanning absolute scoring, classification, and pairwise preference tasks. It is the highest-scoring 8B generative model on RewardBench, surpassing strong baselines like GPT-4o and specialized judges. To achieve this, we develop a principled data curation strategy that augments public datasets with synthetically generated critiques and ensures high qual","authors_text":"Andrei Alexandru, Antonia Calvi, Henry Broomfield, Jackson Golden, Kyle Dai, Mathias Leys, Maurice Burger, Max Bartolo, Roman Engeler, Sashank Pisupati, Toby Drane, Young Sun Park","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T15:09:08Z","title":"Atla Selene Mini: A General Purpose Evaluation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17195","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":"sha256:27517a220a9c1387202d0bee4e2358b66923fcae18cf7704c5e21d462f554c22","target":"record","created_at":"2026-07-05T10:06:48Z","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":"16878597879e2f0ae3f3f9846e791c2219399bca9b92899ca2531b1f254d7094","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T15:09:08Z","title_canon_sha256":"9ec14e8d139f2c00f61b97d6d097c12c6a734053fa485bd44ebc1dccd9114922"},"schema_version":"1.0","source":{"id":"2501.17195","kind":"arxiv","version":1}},"canonical_sha256":"c395c6f489c9485e3427de3e1527e6c576250939a408b583546e20b334776b7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c395c6f489c9485e3427de3e1527e6c576250939a408b583546e20b334776b7f","first_computed_at":"2026-07-05T10:06:48.964555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:48.964555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8bal6DJZd5A+NRRP0AAUESSh8Iqb92JfVV4BQDoROZKYqFI7jmGMbVXRiYkpxMvFHRAQovUHriFcc0z24ydoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:48.965033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27517a220a9c1387202d0bee4e2358b66923fcae18cf7704c5e21d462f554c22","sha256:6146841e2837df84dee0ca62dbd24bfe2a4a1ae0bb143f261f56fc2dcaf327c1"],"state_sha256":"5b5100e811c1eaf9da727d668661e47f052639d3bb7fecc63fbdbd324eb840f5"}