{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y32X4CST5B762NCJSGWYRV4IXZ","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":"ec8eee7f45a8935dba76129bae2739b19a80ff3c25164ad25aa68c30534c0c3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T01:11:01Z","title_canon_sha256":"f1383273af49187ebc70455ebeaac5a7e5a0433401a08e1653e49f748d705332"},"schema_version":"1.0","source":{"id":"2506.17533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17533","created_at":"2026-07-05T11:25:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17533v1","created_at":"2026-07-05T11:25:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17533","created_at":"2026-07-05T11:25:19Z"},{"alias_kind":"pith_short_12","alias_value":"Y32X4CST5B76","created_at":"2026-07-05T11:25:19Z"},{"alias_kind":"pith_short_16","alias_value":"Y32X4CST5B762NCJ","created_at":"2026-07-05T11:25:19Z"},{"alias_kind":"pith_short_8","alias_value":"Y32X4CST","created_at":"2026-07-05T11:25:19Z"}],"graph_snapshots":[{"event_id":"sha256:fd5c7ddb9ef62ca928275531895c309dbd2866ce14e95a1cd6e4ecc8797e8326","target":"graph","created_at":"2026-07-05T11:25:19Z","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/2506.17533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose DuaShepherd, a novel reward modeling framework that integrates two complementary reward signals, correctness and potential, to enhance the mathematical reasoning capabilities of Large Language Models (LLMs). While correctness-based signals emphasize identification of stepwise errors, potential-based signals focus on the likelihood of reaching the correct final answer. We developed an automated pipeline for constructing large-scale reward modeling dataset with both signals. A unified, multi-head architecture was explored to train the two reward models in a multi-task s","authors_text":"Cheng Niu, Hanning Zhang, Juntong Song, Tong Zhang, Yuanhao Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T01:11:01Z","title":"DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17533","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":"sha256:77ae1a72b857bb75b35f3f4aef9a8984fcd262127f446fed4968fda4d2bbdcd4","target":"record","created_at":"2026-07-05T11:25:19Z","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":"ec8eee7f45a8935dba76129bae2739b19a80ff3c25164ad25aa68c30534c0c3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T01:11:01Z","title_canon_sha256":"f1383273af49187ebc70455ebeaac5a7e5a0433401a08e1653e49f748d705332"},"schema_version":"1.0","source":{"id":"2506.17533","kind":"arxiv","version":1}},"canonical_sha256":"c6f57e0a53e87fed344991ad88d788be5ac982178646b097ab389dec033bd0db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f57e0a53e87fed344991ad88d788be5ac982178646b097ab389dec033bd0db","first_computed_at":"2026-07-05T11:25:19.041778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:19.041778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3EkuGX1QMe698LhzrkdqEPEpxstXiO/iIBH4k5Pq49jJrzAvgNG4gvH2nT6Sr4HIrnD/nnzI/h6wG8phIVYpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:19.042247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77ae1a72b857bb75b35f3f4aef9a8984fcd262127f446fed4968fda4d2bbdcd4","sha256:fd5c7ddb9ef62ca928275531895c309dbd2866ce14e95a1cd6e4ecc8797e8326"],"state_sha256":"18dbd298e93c7719c5a407cf8753f45ec4155a4fe467b23008f95acf75814670"}