{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SCBEVL5V5FVE4D2GCURORXMLRA","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":"e92afffe512f276850a525969463f6e05108a81f403083161ab64d8ad40f66ea","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T22:44:58Z","title_canon_sha256":"a47edd30448caee1a01bb298ea40a32a370fc1770393b9261593aa5c2fe431d6"},"schema_version":"1.0","source":{"id":"2605.27747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27747","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27747v1","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27747","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"SCBEVL5V5FVE","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"SCBEVL5V5FVE4D2G","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"SCBEVL5V","created_at":"2026-05-28T01:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:f0e9202c12743c6e1b712770765baeb794f400393f1929b61d6108974a00ffa0","target":"graph","created_at":"2026-05-28T01:04:47Z","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/2605.27747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogeneous, conflicting and often outright contradictory. As a result, the model is forced to compress conflicting goals, and inherent uncertainties into a single, averaged pattern of behaviour. We propose an $\\alpha$-R\\'{e}nyi variational framework for learning distributions over post-training parameters, offering an uncertainty-aware alternative to deep ensemble approaches. The resulting variational objective interpolates between classical variational","authors_text":"Andrew B. Duncan, Georgy Tyukin, Paula Cordero-Encinar","cross_cats":["cs.LG","stat.CO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T22:44:58Z","title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27747","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":"sha256:42bf4233f4f8c1b134bf43a9ae2badbb707e5f6b8b274978cbd6780eefce96ba","target":"record","created_at":"2026-05-28T01:04:47Z","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":"e92afffe512f276850a525969463f6e05108a81f403083161ab64d8ad40f66ea","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T22:44:58Z","title_canon_sha256":"a47edd30448caee1a01bb298ea40a32a370fc1770393b9261593aa5c2fe431d6"},"schema_version":"1.0","source":{"id":"2605.27747","kind":"arxiv","version":1}},"canonical_sha256":"90824aafb5e96a4e0f461522e8dd8b880c22435f738076daddb88bcaae6da958","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90824aafb5e96a4e0f461522e8dd8b880c22435f738076daddb88bcaae6da958","first_computed_at":"2026-05-28T01:04:47.800326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:47.800326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQdicW064tqOvqfILTGpcEKBcOvHdat4Mjd07YCfd+yDrafHfWcS4U7Sr869A+X1U9yT3L65eYkN9WtRE4coDA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:47.800793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42bf4233f4f8c1b134bf43a9ae2badbb707e5f6b8b274978cbd6780eefce96ba","sha256:f0e9202c12743c6e1b712770765baeb794f400393f1929b61d6108974a00ffa0"],"state_sha256":"fbfcc16499b31924429993afd5ffc2abbb268897caeb7d21719a5ad2499cf8d5"}