{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PRXD77GHVSLLAXHBB2CTEWO3PA","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":"80ea73671bcbe11cda5466f9ca35f3d196451f5032dbb749b304440b6c650207","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T15:46:26Z","title_canon_sha256":"76334b005aa82acabf355edd7dd40b1cdf6f57535886294522a6dfd75bcf16dc"},"schema_version":"1.0","source":{"id":"2507.21931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21931","created_at":"2026-07-05T11:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21931v1","created_at":"2026-07-05T11:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21931","created_at":"2026-07-05T11:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"PRXD77GHVSLL","created_at":"2026-07-05T11:45:10Z"},{"alias_kind":"pith_short_16","alias_value":"PRXD77GHVSLLAXHB","created_at":"2026-07-05T11:45:10Z"},{"alias_kind":"pith_short_8","alias_value":"PRXD77GH","created_at":"2026-07-05T11:45:10Z"}],"graph_snapshots":[{"event_id":"sha256:0ff23312b32b685189bd6a3bf7658fb9b5c4fee02760304d3431bb29b91db5c4","target":"graph","created_at":"2026-07-05T11:45:10Z","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/2507.21931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward, mimicking how humans learn in the absence of external feedback. After a frozen LLM generates several chain-of-thought solutions, we define and compute the confidence of each final answer span and rank the traces accordingly. These synthetic preferences are then used to fine-tune the policy with standard preference","authors_text":"Benjamin Matthias Ruppik, Carel van Niekerk, Hsien-Chin Lin, Milica Ga\\v{s}i\\'c, Renato Vukovic","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T15:46:26Z","title":"Post-Training Large Language Models via Reinforcement Learning from Self-Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21931","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:e5d7f7ed74aa8dcf9c173ffdbd1b969fef43433ef9bd36ac248aac27ead2d66e","target":"record","created_at":"2026-07-05T11:45:10Z","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":"80ea73671bcbe11cda5466f9ca35f3d196451f5032dbb749b304440b6c650207","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T15:46:26Z","title_canon_sha256":"76334b005aa82acabf355edd7dd40b1cdf6f57535886294522a6dfd75bcf16dc"},"schema_version":"1.0","source":{"id":"2507.21931","kind":"arxiv","version":1}},"canonical_sha256":"7c6e3ffcc7ac96b05ce10e853259db7838665a45e2f8247acbe1f05e61946987","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c6e3ffcc7ac96b05ce10e853259db7838665a45e2f8247acbe1f05e61946987","first_computed_at":"2026-07-05T11:45:10.011308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:10.011308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W6CtuuYE76T2BqwwLt22abwzFQ4QLtGQqE/hk3zO+SelZ2KG5lX4p6hj2hiF6v8karcLct9To7YjrHhm6d/XAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:10.011882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5d7f7ed74aa8dcf9c173ffdbd1b969fef43433ef9bd36ac248aac27ead2d66e","sha256:0ff23312b32b685189bd6a3bf7658fb9b5c4fee02760304d3431bb29b91db5c4"],"state_sha256":"b751180f8d9f6c5c9429bee84d56acb745ecaa28bf5e7eef0bf61c893ccf45f2"}