{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DZCIQQEJNW6VB6AUWBYNADQEG2","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":"aaae93f5f001b7d323572c0afb3761fbdba7f9afcba5ba6de5f49ebf51f62d1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T07:43:19Z","title_canon_sha256":"3dc0acf149b962945cec8ecc6aa1b44de65e93a77e9e249828ceeb04715b8a7d"},"schema_version":"1.0","source":{"id":"2606.01075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01075","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01075v1","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01075","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"DZCIQQEJNW6V","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"DZCIQQEJNW6VB6AU","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"DZCIQQEJ","created_at":"2026-06-02T01:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:fa5cde31d7852787ca96963c31f870dad7d4c827fb86b8d1ac5db43fbfb2f2bf","target":"graph","created_at":"2026-06-02T01:04:20Z","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/2606.01075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself. In this work, we ask: under a strict closed-loop setup, where the self-evolution algorithm has access only to an unlabeled prompt set and a base model, how close can internally generated supervision come to oracle-supervised training? We analyze four representative strategies in a unified offline self-evolution framework: single-round verification, multi-turn revision with feedback, iterative training, and curriculum learning. Our primary expe","authors_text":"Andrew Tomkins, Cyrus Rashtchian, Da-Cheng Juan, Kan Yuan, Stefanie Anna Baby, Susanna Maria Baby, Tu Vu, Zhenting Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T07:43:19Z","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01075","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":"sha256:352f89829e0d9f7d05f0c2fdb32dd977229360d4ffc1573d0f62554a95be02db","target":"record","created_at":"2026-06-02T01:04:20Z","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":"aaae93f5f001b7d323572c0afb3761fbdba7f9afcba5ba6de5f49ebf51f62d1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T07:43:19Z","title_canon_sha256":"3dc0acf149b962945cec8ecc6aa1b44de65e93a77e9e249828ceeb04715b8a7d"},"schema_version":"1.0","source":{"id":"2606.01075","kind":"arxiv","version":1}},"canonical_sha256":"1e448840896dbd50f814b070d00e0436921df6961afb250effe8345c9aeac6bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e448840896dbd50f814b070d00e0436921df6961afb250effe8345c9aeac6bd","first_computed_at":"2026-06-02T01:04:20.595559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:20.595559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cp7GGTRjMeU27q/gQlaEpLD4rR9h4YAn1HTsCON2uwBbkiYWj9DCNua0jGKUMnAgmXZxukJ05/b7gyLiVnPLDA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:20.595984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:352f89829e0d9f7d05f0c2fdb32dd977229360d4ffc1573d0f62554a95be02db","sha256:fa5cde31d7852787ca96963c31f870dad7d4c827fb86b8d1ac5db43fbfb2f2bf"],"state_sha256":"414294ce074f7c4fc3727ec9e663a2f73efcb7ae68533d2caecff4ca3aa5ecdf"}