{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CCXVZPOLHD34TWKTAXCEJHKXFK","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":"1637ca88c63613a7f587c2a968f0febd1a3c06ddb4276e70667f73c0e141118d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T06:27:37Z","title_canon_sha256":"18c0dae955de89151cfba0a610d27153290561962c97d8ac9cda9716ae38c89a"},"schema_version":"1.0","source":{"id":"2606.08471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08471","created_at":"2026-06-09T01:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08471v1","created_at":"2026-06-09T01:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08471","created_at":"2026-06-09T01:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"CCXVZPOLHD34","created_at":"2026-06-09T01:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"CCXVZPOLHD34TWKT","created_at":"2026-06-09T01:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"CCXVZPOL","created_at":"2026-06-09T01:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:665818b3a47e709e6779608b70929b15bf00bd2243ab99560502585dd49765dc","target":"graph","created_at":"2026-06-09T01:05:37Z","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/2606.08471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, language models have made rapid progress across various domains and applications. However, their capability for self-improvement, i.e., whether they are adept at recognising and correcting flaws in their own reasoning, remains dubious. In this study, we address this question by constructing a sufficiency test to rigorously examine the self-correction capabilities of small language models (SLMs). We propose a minimal three-step self-correction pipeline that collects initial SLM answers, prompts the same model to generate hints for its incorrect responses given the ground truth, and fe","authors_text":"Erik Arakelyan, Marina Igitkhanian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T06:27:37Z","title":"More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08471","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:f0d33e8974b7eb2e826dee5d75c71a02684fe60915148734cbab06f30ebd03e7","target":"record","created_at":"2026-06-09T01:05:37Z","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":"1637ca88c63613a7f587c2a968f0febd1a3c06ddb4276e70667f73c0e141118d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T06:27:37Z","title_canon_sha256":"18c0dae955de89151cfba0a610d27153290561962c97d8ac9cda9716ae38c89a"},"schema_version":"1.0","source":{"id":"2606.08471","kind":"arxiv","version":1}},"canonical_sha256":"10af5cbdcb38f7c9d95305c4449d572aa7d4d2627f9cd7bfbed819a7cbec939f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10af5cbdcb38f7c9d95305c4449d572aa7d4d2627f9cd7bfbed819a7cbec939f","first_computed_at":"2026-06-09T01:05:37.560926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:37.560926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fcig2mpER1zrx1JmcLD2BG+2Fa3qexuStK3JxwFFVZAh4DojEyBge7U2TZVU772jWAUgKXgMpRvigflQV0RACw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:37.561344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0d33e8974b7eb2e826dee5d75c71a02684fe60915148734cbab06f30ebd03e7","sha256:665818b3a47e709e6779608b70929b15bf00bd2243ab99560502585dd49765dc"],"state_sha256":"2cc5904255e4794a76db8611302b7d60969a70821305734ad7d1b70d07003e8a"}