{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3N35E2S3P6XIHBDHDZGRKUBNH6","short_pith_number":"pith:3N35E2S3","canonical_record":{"source":{"id":"2607.01612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:29:33Z","cross_cats_sorted":[],"title_canon_sha256":"75c8bc537aa8cf6b9f2adf1ba8baa3200d4dac2d62d62cb6e16c3659c5b177cb","abstract_canon_sha256":"7891a59388006cad26103417b4e4b0a97274c1343ae7fae51b9c19c28fc36d78"},"schema_version":"1.0"},"canonical_sha256":"db77d26a5b7fae8384671e4d15502d3f955219abed3776cac661158cf5c49748","source":{"kind":"arxiv","id":"2607.01612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01612","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01612v1","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01612","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"3N35E2S3P6XI","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"3N35E2S3P6XIHBDH","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"3N35E2S3","created_at":"2026-07-03T01:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3N35E2S3P6XIHBDHDZGRKUBNH6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:29:33Z","cross_cats_sorted":[],"title_canon_sha256":"75c8bc537aa8cf6b9f2adf1ba8baa3200d4dac2d62d62cb6e16c3659c5b177cb","abstract_canon_sha256":"7891a59388006cad26103417b4e4b0a97274c1343ae7fae51b9c19c28fc36d78"},"schema_version":"1.0"},"canonical_sha256":"db77d26a5b7fae8384671e4d15502d3f955219abed3776cac661158cf5c49748","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:03.345117Z","signature_b64":"j57eYL7gd8xb4pCjkTOfUr0CiESImXg1sdT/TLtEFyM4DngMoH1UvsbVb3FfHtVhdSkYjGv1WZKj6YFwClGsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db77d26a5b7fae8384671e4d15502d3f955219abed3776cac661158cf5c49748","last_reissued_at":"2026-07-03T01:17:03.344721Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:03.344721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01612","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":"2026-07-03T01:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdSP89VY61R3pciADUrNPUgtE6maMykuKT90mPSUP6lVr8YWTL9TBG+jdIL8R5Z96KsD2eag+627CEcCJnwaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:20:55.361342Z"},"content_sha256":"39c0e9893b8b6cbfc6c61121a75e809c570e078a4c2d5fd808930b8235763f26","schema_version":"1.0","event_id":"sha256:39c0e9893b8b6cbfc6c61121a75e809c570e078a4c2d5fd808930b8235763f26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3N35E2S3P6XIHBDHDZGRKUBNH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shanzhe Lei, Xuhong Wang, Xuqing Yang, Yi Yuan","submitted_at":"2026-07-02T02:29:33Z","abstract_excerpt":"Training large language models (LLMs) with reinforcement learning (RL) has significantly advanced their performance on reasoning and question-answering tasks. However, prevailing RL reward designs typically prioritize response correctness, neglecting to incentivize models to express their confidence accurately. This leads to a critical problem: performance gains are often accompanied by poor calibration between confidence and accuracy, misleading models to overconfidently hallucinate when uncertain. To address this limitation, we propose $\\textbf{C}$orrectness and $\\textbf{C}$onfidence $\\textb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01612","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/2607.01612/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-03T01:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QIBlmMeIl3Fbw+Rl6+wqbf17YLvRIEyrLilqV9ZhZ1KoChA2SOePW/sHBnWy5wNK38eJi1H6j7A9/RPupjVxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:20:55.361721Z"},"content_sha256":"1772bd28c6dd386d9b193537a07773bf130ec16e27c5a515942209da49bdabda","schema_version":"1.0","event_id":"sha256:1772bd28c6dd386d9b193537a07773bf130ec16e27c5a515942209da49bdabda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/bundle.json","state_url":"https://pith.science/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/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":"2026-07-04T12:20:55Z","links":{"resolver":"https://pith.science/pith/3N35E2S3P6XIHBDHDZGRKUBNH6","bundle":"https://pith.science/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/bundle.json","state":"https://pith.science/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3N35E2S3P6XIHBDHDZGRKUBNH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3N35E2S3P6XIHBDHDZGRKUBNH6","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":"7891a59388006cad26103417b4e4b0a97274c1343ae7fae51b9c19c28fc36d78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:29:33Z","title_canon_sha256":"75c8bc537aa8cf6b9f2adf1ba8baa3200d4dac2d62d62cb6e16c3659c5b177cb"},"schema_version":"1.0","source":{"id":"2607.01612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01612","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01612v1","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01612","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"3N35E2S3P6XI","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"3N35E2S3P6XIHBDH","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"3N35E2S3","created_at":"2026-07-03T01:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:1772bd28c6dd386d9b193537a07773bf130ec16e27c5a515942209da49bdabda","target":"graph","created_at":"2026-07-03T01:17:03Z","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/2607.01612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) with reinforcement learning (RL) has significantly advanced their performance on reasoning and question-answering tasks. However, prevailing RL reward designs typically prioritize response correctness, neglecting to incentivize models to express their confidence accurately. This leads to a critical problem: performance gains are often accompanied by poor calibration between confidence and accuracy, misleading models to overconfidently hallucinate when uncertain. To address this limitation, we propose $\\textbf{C}$orrectness and $\\textbf{C}$onfidence $\\textb","authors_text":"Shanzhe Lei, Xuhong Wang, Xuqing Yang, Yi Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:29:33Z","title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01612","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":"sha256:39c0e9893b8b6cbfc6c61121a75e809c570e078a4c2d5fd808930b8235763f26","target":"record","created_at":"2026-07-03T01:17:03Z","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":"7891a59388006cad26103417b4e4b0a97274c1343ae7fae51b9c19c28fc36d78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:29:33Z","title_canon_sha256":"75c8bc537aa8cf6b9f2adf1ba8baa3200d4dac2d62d62cb6e16c3659c5b177cb"},"schema_version":"1.0","source":{"id":"2607.01612","kind":"arxiv","version":1}},"canonical_sha256":"db77d26a5b7fae8384671e4d15502d3f955219abed3776cac661158cf5c49748","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db77d26a5b7fae8384671e4d15502d3f955219abed3776cac661158cf5c49748","first_computed_at":"2026-07-03T01:17:03.344721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:03.344721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j57eYL7gd8xb4pCjkTOfUr0CiESImXg1sdT/TLtEFyM4DngMoH1UvsbVb3FfHtVhdSkYjGv1WZKj6YFwClGsBg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:03.345117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39c0e9893b8b6cbfc6c61121a75e809c570e078a4c2d5fd808930b8235763f26","sha256:1772bd28c6dd386d9b193537a07773bf130ec16e27c5a515942209da49bdabda"],"state_sha256":"b6e67a6996656fc116811beb3943ceeb3949386bcb268ff657d0e3d5ba071309"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L4WEg55GLobgIgXXqb4/4BBIW+zuzOEPlqWjsKjaxehtTY2mZN2phkS81qPEAMSYfMXU8Itw2Awwzg15WfNBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T12:20:55.363784Z","bundle_sha256":"e0e3ccaa6b61851ed5f929c9d7cd5aa425b359d5ab386f41c1fb0e051dfcdf42"}}