{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2IEU4N5BQDITH2APSFKOQZ5NAZ","short_pith_number":"pith:2IEU4N5B","canonical_record":{"source":{"id":"2607.04332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:29:18Z","cross_cats_sorted":[],"title_canon_sha256":"e74c4d411d744b588d67271890ede775482d29c1ad9c815e1c962543b11fedea","abstract_canon_sha256":"4a32da4e3f64265ff258e6b40a8709afa1f60c1cb3c24e0c2bff422e493b397b"},"schema_version":"1.0"},"canonical_sha256":"d2094e37a180d133e80f9154e867ad0659f29db4caa893524695a983bf9b1a35","source":{"kind":"arxiv","id":"2607.04332","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04332","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04332v1","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04332","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"2IEU4N5BQDIT","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"2IEU4N5BQDITH2AP","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"2IEU4N5B","created_at":"2026-07-07T02:19:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2IEU4N5BQDITH2APSFKOQZ5NAZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:29:18Z","cross_cats_sorted":[],"title_canon_sha256":"e74c4d411d744b588d67271890ede775482d29c1ad9c815e1c962543b11fedea","abstract_canon_sha256":"4a32da4e3f64265ff258e6b40a8709afa1f60c1cb3c24e0c2bff422e493b397b"},"schema_version":"1.0"},"canonical_sha256":"d2094e37a180d133e80f9154e867ad0659f29db4caa893524695a983bf9b1a35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:09.510762Z","signature_b64":"cPpbDQ0X+6K4JSZVlbugarkvgnxJu8E0axOcLwnAxbRKcVepZcAAnOEVckKDEKvEmInsKi78/FqSY6rSrMMxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2094e37a180d133e80f9154e867ad0659f29db4caa893524695a983bf9b1a35","last_reissued_at":"2026-07-07T02:19:09.510100Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:09.510100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04332","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":"2026-07-07T02:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JPdL2xATtFzBaV2FbiLuhExvO4a0Zsh31ebGd5HpR1o+y46NgmS9jstGMkW1bZ+Wiqjw+8dx+BCB7oWhMbqdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T07:09:38.751502Z"},"content_sha256":"751173da1e39b4f081ab944c58b1a970a7b6bf7399d0de8469bf6b21385a6070","schema_version":"1.0","event_id":"sha256:751173da1e39b4f081ab944c58b1a970a7b6bf7399d0de8469bf6b21385a6070"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2IEU4N5BQDITH2APSFKOQZ5NAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chee Heng Tan, Mehul Motani, Wee Sun Lee, Zhuoyi Lin","submitted_at":"2026-07-05T14:29:18Z","abstract_excerpt":"In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reasoning accuracy and verbalize its confidence. Our reward scheme uses two functions for rewarding confidence verbalized by the LLM: one when the LLM is correct and a different one when the LLM is incorrect. With a poorly designed reward scheme, the LLM may be incentivized to answer incorrectly so that it can be confident that its answer is indeed incorrect, a phenomenon that we call confidence reward hacking. We propose the concept of non-hackable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04332","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/2607.04332/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":"2026-07-07T02:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z4OADW/j9/MRoReBFDcl6G9vPuCSih7rrnSEhduTOXKYnyyubhq+ETHvl6XcSutS6G3p9emrVX4oilkXcX/6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T07:09:38.752125Z"},"content_sha256":"ceed08f94d8e61e2c493f378866f595208e9bd9e0f989f388870fc3c8404bef6","schema_version":"1.0","event_id":"sha256:ceed08f94d8e61e2c493f378866f595208e9bd9e0f989f388870fc3c8404bef6"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:2IEU4N5BQDITH2APSFKOQZ5NAZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1175/1520-0493(1950)078<0001:vofeit>) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"G. W. Brier, “Verification of forecasts expressed in terms of probability,”Monthly weather review, vol. 78, no. 1, pp. 1–3, 1950.DOI: 10.1175/1520-0493(1950)078<0001:vofeit> 2.0.co;2","arxiv_id":"2607.04332","detector":"doi_compliance","evidence":{"ref_index":37,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"G. W. Brier, “Verification of forecasts expressed in terms of probability,”Monthly weather review, vol. 78, no. 1, pp. 1–3, 1950.DOI: 10.1175/1520-0493(1950)078<0001:vofeit> 2.0.co;2","reconstructed_doi":"10.1175/1520-0493(1950)078<0001:vofeit>"},"severity":"advisory","ref_index":37,"audited_at":"2026-07-11T20:04:41.595980Z","event_type":"pith.integrity.v1","detected_doi":"10.1175/1520-0493(1950)078<0001:vofeit>","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5d199d69d3466ad00f8a54d3c11ff9e0d9cbbc230728603838cfaf18792da397","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12263,"payload_sha256":"d3470d9d324848b06f6e0c4bd810d1b0b72ec444fc98d78af974d991fed390a1","signature_b64":"ckSYH0byQ2QCtMsxlwcmtMW1yabh1E0peMQp3QDn3EPd+LCNmf1mCv736eTOVKJRd0JVka+vD2+GS54lmtmdCw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T20:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vVAbwXe68y5+JTfk8QMsGbWLoe+oWOCCxNcJCG/7b9BUc1HVbE61SqwOX1wTboLvVpzSuU6SEYgdZp8JGCG6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T07:09:38.757352Z"},"content_sha256":"cf78d1da7cedc909ea967e67218561b9660ca22d525c678b982b9b058c0d4735","schema_version":"1.0","event_id":"sha256:cf78d1da7cedc909ea967e67218561b9660ca22d525c678b982b9b058c0d4735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/bundle.json","state_url":"https://pith.science/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/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":"2026-08-03T07:09:38Z","links":{"resolver":"https://pith.science/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ","bundle":"https://pith.science/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/bundle.json","state":"https://pith.science/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2IEU4N5BQDITH2APSFKOQZ5NAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2IEU4N5BQDITH2APSFKOQZ5NAZ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4a32da4e3f64265ff258e6b40a8709afa1f60c1cb3c24e0c2bff422e493b397b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:29:18Z","title_canon_sha256":"e74c4d411d744b588d67271890ede775482d29c1ad9c815e1c962543b11fedea"},"schema_version":"1.0","source":{"id":"2607.04332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04332","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04332v1","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04332","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"2IEU4N5BQDIT","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"2IEU4N5BQDITH2AP","created_at":"2026-07-07T02:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"2IEU4N5B","created_at":"2026-07-07T02:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:ceed08f94d8e61e2c493f378866f595208e9bd9e0f989f388870fc3c8404bef6","target":"graph","created_at":"2026-07-07T02:19:09Z","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/2607.04332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reasoning accuracy and verbalize its confidence. Our reward scheme uses two functions for rewarding confidence verbalized by the LLM: one when the LLM is correct and a different one when the LLM is incorrect. With a poorly designed reward scheme, the LLM may be incentivized to answer incorrectly so that it can be confident that its answer is indeed incorrect, a phenomenon that we call confidence reward hacking. We propose the concept of non-hackable ","authors_text":"Chee Heng Tan, Mehul Motani, Wee Sun Lee, Zhuoyi Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:29:18Z","title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04332","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":"sha256:751173da1e39b4f081ab944c58b1a970a7b6bf7399d0de8469bf6b21385a6070","target":"record","created_at":"2026-07-07T02:19:09Z","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":"4a32da4e3f64265ff258e6b40a8709afa1f60c1cb3c24e0c2bff422e493b397b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T14:29:18Z","title_canon_sha256":"e74c4d411d744b588d67271890ede775482d29c1ad9c815e1c962543b11fedea"},"schema_version":"1.0","source":{"id":"2607.04332","kind":"arxiv","version":1}},"canonical_sha256":"d2094e37a180d133e80f9154e867ad0659f29db4caa893524695a983bf9b1a35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2094e37a180d133e80f9154e867ad0659f29db4caa893524695a983bf9b1a35","first_computed_at":"2026-07-07T02:19:09.510100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:09.510100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPpbDQ0X+6K4JSZVlbugarkvgnxJu8E0axOcLwnAxbRKcVepZcAAnOEVckKDEKvEmInsKi78/FqSY6rSrMMxCA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:09.510762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751173da1e39b4f081ab944c58b1a970a7b6bf7399d0de8469bf6b21385a6070","sha256:ceed08f94d8e61e2c493f378866f595208e9bd9e0f989f388870fc3c8404bef6","sha256:cf78d1da7cedc909ea967e67218561b9660ca22d525c678b982b9b058c0d4735"],"state_sha256":"d5f579e947025bd90324d591f6ab8ba48d0e504dcb04571f816249b9a488c7cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4MJjW89ibqgvHTWF4WsFhFgMw4nH1pSdcfEtGUhvWX7/XJRB+8xNUy5zXcjcevmSo+2aRYSMa6JC2/Qdh3GCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T07:09:38.759706Z","bundle_sha256":"e5e67174e7994058b6cbb4ce036fc6da5eaf703d04ca737ed21819997764f104"}}