{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ISXL2LIVGPUQZK7WVCNWC47HLP","short_pith_number":"pith:ISXL2LIV","canonical_record":{"source":{"id":"2605.15588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dcba01a3fbb10ee7ab4994076d6ed9ddde7e7091b5bc94eaef462d18e700a6ef","abstract_canon_sha256":"66fd3a229447d27590bdb7abf4586ddcaaab28cbfeac706c777e3088a595af14"},"schema_version":"1.0"},"canonical_sha256":"44aebd2d1533e90cabf6a89b6173e75bd591e3267231cbad1b403bae4043db9c","source":{"kind":"arxiv","id":"2605.15588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15588","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15588v1","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15588","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_12","alias_value":"ISXL2LIVGPUQ","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_16","alias_value":"ISXL2LIVGPUQZK7W","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_8","alias_value":"ISXL2LIV","created_at":"2026-05-20T00:01:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ISXL2LIVGPUQZK7WVCNWC47HLP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dcba01a3fbb10ee7ab4994076d6ed9ddde7e7091b5bc94eaef462d18e700a6ef","abstract_canon_sha256":"66fd3a229447d27590bdb7abf4586ddcaaab28cbfeac706c777e3088a595af14"},"schema_version":"1.0"},"canonical_sha256":"44aebd2d1533e90cabf6a89b6173e75bd591e3267231cbad1b403bae4043db9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:06.858267Z","signature_b64":"nck2E/nm0clHaHUqTmjwjfXk/4JMFHQi3k5zXBVBL+6LxG4rLcz52ksLdDihvQ92/A+zyRq1kvFJbXGvej6gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44aebd2d1533e90cabf6a89b6173e75bd591e3267231cbad1b403bae4043db9c","last_reissued_at":"2026-05-20T00:01:06.857475Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:06.857475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15588","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtlfMx8OyqmOw1oP8PiKl9sWcmv/M5NyT5VYCbgrd/1/QweYwfvCxLVbq8vvanYJrK1h1Xkqugusu2sQrhWTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:53:26.986995Z"},"content_sha256":"73d3e22709c0e5374d6cc57947f4e383f346fa5b5a5d4154b578feba3a0d14fe","schema_version":"1.0","event_id":"sha256:73d3e22709c0e5374d6cc57947f4e383f346fa5b5a5d4154b578feba3a0d14fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ISXL2LIVGPUQZK7WVCNWC47HLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrating LLMs with Semantic-level Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dongxia Wu, Fengfei Yu, Rose Yu, Ruijia Niu, Yian Ma","submitted_at":"2026-05-15T03:55:11Z","abstract_excerpt":"As large language models (LLMs) are deployed in consequential settings such as medical question answering and legal reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use, requiring well-calibrated uncertainty. Standard reinforcement learning with verifiable rewards (RLVR) trains models with a binary correctness reward that is indifferent to confidence, providing no penalty for confident but wrong predictions and thereby degrading calibration. Recent work addresses this by training models to produce verbalized confidence scores alo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15588","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15588/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.243460Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.065039Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7bfc34297c00b094d6976d37fc21c7ea8469f580c12a1ec8b796a379f13b9786"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8W53Ci4d0SPFfV3k5MQk69uWfHmf6TLHdmo6JOSLz5ZT4aVxksjP7rmochkRKVb17qmas64Ir0iOuV8XBkqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:53:26.987626Z"},"content_sha256":"168c839c0e2493a664ba156d0f5fb1023afff66fa98a6216a0549b2b73b26b6f","schema_version":"1.0","event_id":"sha256:168c839c0e2493a664ba156d0f5fb1023afff66fa98a6216a0549b2b73b26b6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/bundle.json","state_url":"https://pith.science/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T17:53:26Z","links":{"resolver":"https://pith.science/pith/ISXL2LIVGPUQZK7WVCNWC47HLP","bundle":"https://pith.science/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/bundle.json","state":"https://pith.science/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISXL2LIVGPUQZK7WVCNWC47HLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ISXL2LIVGPUQZK7WVCNWC47HLP","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":"66fd3a229447d27590bdb7abf4586ddcaaab28cbfeac706c777e3088a595af14","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:55:11Z","title_canon_sha256":"dcba01a3fbb10ee7ab4994076d6ed9ddde7e7091b5bc94eaef462d18e700a6ef"},"schema_version":"1.0","source":{"id":"2605.15588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15588","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15588v1","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15588","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_12","alias_value":"ISXL2LIVGPUQ","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_16","alias_value":"ISXL2LIVGPUQZK7W","created_at":"2026-05-20T00:01:06Z"},{"alias_kind":"pith_short_8","alias_value":"ISXL2LIV","created_at":"2026-05-20T00:01:06Z"}],"graph_snapshots":[{"event_id":"sha256:168c839c0e2493a664ba156d0f5fb1023afff66fa98a6216a0549b2b73b26b6f","target":"graph","created_at":"2026-05-20T00:01:06Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.243460Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.065039Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15588/integrity.json","findings":[],"snapshot_sha256":"7bfc34297c00b094d6976d37fc21c7ea8469f580c12a1ec8b796a379f13b9786","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) are deployed in consequential settings such as medical question answering and legal reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use, requiring well-calibrated uncertainty. Standard reinforcement learning with verifiable rewards (RLVR) trains models with a binary correctness reward that is indifferent to confidence, providing no penalty for confident but wrong predictions and thereby degrading calibration. Recent work addresses this by training models to produce verbalized confidence scores alo","authors_text":"Dongxia Wu, Fengfei Yu, Rose Yu, Ruijia Niu, Yian Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:55:11Z","title":"Calibrating LLMs with Semantic-level Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15588","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":"sha256:73d3e22709c0e5374d6cc57947f4e383f346fa5b5a5d4154b578feba3a0d14fe","target":"record","created_at":"2026-05-20T00:01:06Z","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":"66fd3a229447d27590bdb7abf4586ddcaaab28cbfeac706c777e3088a595af14","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:55:11Z","title_canon_sha256":"dcba01a3fbb10ee7ab4994076d6ed9ddde7e7091b5bc94eaef462d18e700a6ef"},"schema_version":"1.0","source":{"id":"2605.15588","kind":"arxiv","version":1}},"canonical_sha256":"44aebd2d1533e90cabf6a89b6173e75bd591e3267231cbad1b403bae4043db9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44aebd2d1533e90cabf6a89b6173e75bd591e3267231cbad1b403bae4043db9c","first_computed_at":"2026-05-20T00:01:06.857475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:06.857475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nck2E/nm0clHaHUqTmjwjfXk/4JMFHQi3k5zXBVBL+6LxG4rLcz52ksLdDihvQ92/A+zyRq1kvFJbXGvej6gDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:06.858267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d3e22709c0e5374d6cc57947f4e383f346fa5b5a5d4154b578feba3a0d14fe","sha256:168c839c0e2493a664ba156d0f5fb1023afff66fa98a6216a0549b2b73b26b6f"],"state_sha256":"d444fe3d8ea305efcb5e78780ef38f1d09c2311570988fe6ac74bb39fe472bd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WwVBtf+h95IUNgIHb2LTfVnsD42xcdDF/0C70nLI8yjkeGiFJENqu3MLd70TpVNaRYxdKSE8J+6qxtpxN8IJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:53:26.990620Z","bundle_sha256":"542196605d02fa0fbfdd8e15476752caefac9590c15188e844edf685d32ccd3e"}}