{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JW3P3BR2ISD6ZAVXRCS6HU324Z","short_pith_number":"pith:JW3P3BR2","canonical_record":{"source":{"id":"2607.29185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"e8c4b95eb12d524a81da90b13a4a4ad607632f84d573d12e264d8f1dbab1fb82","abstract_canon_sha256":"a2c5e1c02bd90f5d4420d3fe7de0d2462c7e4335b3beb4e6458b9f40b6af5f34"},"schema_version":"1.0"},"canonical_sha256":"4db6fd863a4487ec82b788a5e3d37ae64501a8a5280b0a470f0d496e5562a602","source":{"kind":"arxiv","id":"2607.29185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29185","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29185v1","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29185","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"JW3P3BR2ISD6","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"JW3P3BR2ISD6ZAVX","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"JW3P3BR2","created_at":"2026-08-03T01:20:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JW3P3BR2ISD6ZAVXRCS6HU324Z","target":"record","payload":{"canonical_record":{"source":{"id":"2607.29185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"e8c4b95eb12d524a81da90b13a4a4ad607632f84d573d12e264d8f1dbab1fb82","abstract_canon_sha256":"a2c5e1c02bd90f5d4420d3fe7de0d2462c7e4335b3beb4e6458b9f40b6af5f34"},"schema_version":"1.0"},"canonical_sha256":"4db6fd863a4487ec82b788a5e3d37ae64501a8a5280b0a470f0d496e5562a602","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:20:37.460416Z","signature_b64":"lpqbBNAgElrEqDSFSMUisPAdkIFDpmaR7c0Fi8poEuwoR42Cd8EXBqn9KrPjdBZ+vDbr4YWg8KjvXLCPojR5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db6fd863a4487ec82b788a5e3d37ae64501a8a5280b0a470f0d496e5562a602","last_reissued_at":"2026-08-03T01:20:37.458704Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:20:37.458704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.29185","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":"2026-08-03T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mP+bHqs9MDxv3iNlS3U7Gs/+SMRrqq+hABDpP0hJmAS1G5ArOSWEZeHt42DXFjq6CMU0u943EwYpe2lUI7kyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:46:28.041551Z"},"content_sha256":"2befb88f616ddc93802dd56519c06e43f709ae9035dfeb039a216b3d9c76bb8a","schema_version":"1.0","event_id":"sha256:2befb88f616ddc93802dd56519c06e43f709ae9035dfeb039a216b3d9c76bb8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JW3P3BR2ISD6ZAVXRCS6HU324Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Latent Reasoning Traces for Scalar Reward Models End-to-End","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clive Bai, Hsiu-Yuan Huang, Kun Liang, Sanwoo Lee, Weijie Liu, Yunfang Wu","submitted_at":"2026-07-31T09:05:58Z","abstract_excerpt":"Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilistic reward modeling, they rely on superficial cues that fail to generalize to complex or out-of-distribution (OOD) tasks. Conversely, generative RMs leverage extensive reasoning to improve robustness on challenging tasks, but their natural language-based scores lack the numerical flexibility and probabilistic interpretability that scalar RMs offer. While recent approaches combine both paradigms through off-policy mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29185","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/2607.29185/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":"2026-08-03T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSmDPHuRSthy5ecggbxxbeFIKIlfyQ8mLL+WCpHzXXyN4+7vZ4L6L9/ogtYmMf+pedhaA+rDUJd6kKcd8iVDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:46:28.041930Z"},"content_sha256":"00bbac9393a4269ca739d4d48494d27a8e162145925927377508bc3888e8584a","schema_version":"1.0","event_id":"sha256:00bbac9393a4269ca739d4d48494d27a8e162145925927377508bc3888e8584a"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:JW3P3BR2ISD6ZAVXRCS6HU324Z","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2025.naacl-long.573) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Yu, Yue and Chen, Zhengxing and Zhang, Aston and Tan, Liang and Zhu, Chenguang and Pang, Richard Yuanzhe and Qian, Yundi and Wang, Xuewei and Gururangan, Suchin and Zhang, Chao and Kambadur, Melanie and Mahajan, Dhruv and Hou, Rui. Self-Gen","arxiv_id":"2607.29185","detector":"doi_compliance","evidence":{"ref_index":12,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2","reconstructed_doi":"10.18653/v1/2025.naacl-long.573"},"severity":"advisory","ref_index":12,"audited_at":"2026-08-03T12:18:10.890645Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2025.naacl-long.573","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"c67b0240562295e963003b81bc99e7c53a3472bcda79e10aae213393b261fa81","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17621,"payload_sha256":"35a5bf11fcaece5cf457ae308dd943a5e40dd766e536f619cf8e9afe774f0022","signature_b64":"8fSq7UbhuNedW18OMmm8FkFmPTdQNXvMmZkjIQWSEjHquwnDvJe3yYgnvdRehst0TuItA/A3DVWo92BeIK/tDQ==","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":"2026-08-03T12:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgT+32weMTXn7CGmnsEjdKTPZfH425V2KeTLvBQUOvlyp2LTFxDsCBa+cm6DHjad/Le/7HH5qYNULIyKxoovDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:46:28.044114Z"},"content_sha256":"446d6f4a5f57e1555f8968deed03f479b3f41745e47c915ba598247d0d277a86","schema_version":"1.0","event_id":"sha256:446d6f4a5f57e1555f8968deed03f479b3f41745e47c915ba598247d0d277a86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/bundle.json","state_url":"https://pith.science/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/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":"2026-08-04T06:46:28Z","links":{"resolver":"https://pith.science/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z","bundle":"https://pith.science/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/bundle.json","state":"https://pith.science/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW3P3BR2ISD6ZAVXRCS6HU324Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JW3P3BR2ISD6ZAVXRCS6HU324Z","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":"a2c5e1c02bd90f5d4420d3fe7de0d2462c7e4335b3beb4e6458b9f40b6af5f34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:05:58Z","title_canon_sha256":"e8c4b95eb12d524a81da90b13a4a4ad607632f84d573d12e264d8f1dbab1fb82"},"schema_version":"1.0","source":{"id":"2607.29185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29185","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29185v1","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29185","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"JW3P3BR2ISD6","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"JW3P3BR2ISD6ZAVX","created_at":"2026-08-03T01:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"JW3P3BR2","created_at":"2026-08-03T01:20:37Z"}],"graph_snapshots":[{"event_id":"sha256:00bbac9393a4269ca739d4d48494d27a8e162145925927377508bc3888e8584a","target":"graph","created_at":"2026-08-03T01:20:37Z","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/2607.29185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilistic reward modeling, they rely on superficial cues that fail to generalize to complex or out-of-distribution (OOD) tasks. Conversely, generative RMs leverage extensive reasoning to improve robustness on challenging tasks, but their natural language-based scores lack the numerical flexibility and probabilistic interpretability that scalar RMs offer. While recent approaches combine both paradigms through off-policy mul","authors_text":"Clive Bai, Hsiu-Yuan Huang, Kun Liang, Sanwoo Lee, Weijie Liu, Yunfang Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:05:58Z","title":"Learning Latent Reasoning Traces for Scalar Reward Models End-to-End"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29185","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":"sha256:2befb88f616ddc93802dd56519c06e43f709ae9035dfeb039a216b3d9c76bb8a","target":"record","created_at":"2026-08-03T01:20:37Z","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":"a2c5e1c02bd90f5d4420d3fe7de0d2462c7e4335b3beb4e6458b9f40b6af5f34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:05:58Z","title_canon_sha256":"e8c4b95eb12d524a81da90b13a4a4ad607632f84d573d12e264d8f1dbab1fb82"},"schema_version":"1.0","source":{"id":"2607.29185","kind":"arxiv","version":1}},"canonical_sha256":"4db6fd863a4487ec82b788a5e3d37ae64501a8a5280b0a470f0d496e5562a602","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4db6fd863a4487ec82b788a5e3d37ae64501a8a5280b0a470f0d496e5562a602","first_computed_at":"2026-08-03T01:20:37.458704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:20:37.458704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lpqbBNAgElrEqDSFSMUisPAdkIFDpmaR7c0Fi8poEuwoR42Cd8EXBqn9KrPjdBZ+vDbr4YWg8KjvXLCPojR5DA==","signature_status":"signed_v1","signed_at":"2026-08-03T01:20:37.460416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2befb88f616ddc93802dd56519c06e43f709ae9035dfeb039a216b3d9c76bb8a","sha256:00bbac9393a4269ca739d4d48494d27a8e162145925927377508bc3888e8584a","sha256:446d6f4a5f57e1555f8968deed03f479b3f41745e47c915ba598247d0d277a86"],"state_sha256":"02b186506a08f3ab662600f7507370eeddd0793273df591e27568ba635f61786"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IEuf++n1GExvfIecovb9oiogQau2BhnGCG730eQGzR3vfKW6QpX6FQsgZTvejTz6odYtBME0XPbIeGQGM7BMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:46:28.045619Z","bundle_sha256":"08e45359f3afcbba6b93f209d8edf8f7461719aef51672b9663f712e244cb95b"}}