{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JV4EROTNPOHFGOJAPTCF663VGY","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":"f1515d7bd8d00201a52a7574434199fa89cd468f39c31d1597dcf2b8932ba7a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:39:56Z","title_canon_sha256":"e465d6203557af2580c234961856932e5f2a9dfa8d6934de738bd3c92fe9bcbc"},"schema_version":"1.0","source":{"id":"2505.07787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07787","created_at":"2026-07-05T11:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07787v1","created_at":"2026-07-05T11:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07787","created_at":"2026-07-05T11:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"JV4EROTNPOHF","created_at":"2026-07-05T11:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"JV4EROTNPOHFGOJA","created_at":"2026-07-05T11:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"JV4EROTN","created_at":"2026-07-05T11:01:53Z"}],"graph_snapshots":[{"event_id":"sha256:0a5a68d537cba9a4ce9ef2f809634625aca86edfa82ace7f51f03f8f227c54ae","target":"graph","created_at":"2026-07-05T11:01:53Z","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/2505.07787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process starts with a short but poor beginning, it becomes difficult for the model to recover. We refer to this phenomenon as the \"Prefix Dominance Trap\". Inspired by psychological findings that peer interaction can promote self-correction without negatively impacting already accurate individuals, we propose **Learning from Peers** (LeaP) to address this phenomenon. Specifically, every tokens, each reasoning path summarizes its","authors_text":"Benyou Wang, Hao Yang, Jiaxi Bi, Min Zhang, Stephen Chung, Tongxu Luo, Wenyu Du, Zhengyang Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:39:56Z","title":"Learning from Peers in Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07787","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":"sha256:40b2d48aa42989ad9ef3cefcb50b1e74fe43ac826e4ec629e093352b842b005b","target":"record","created_at":"2026-07-05T11:01:53Z","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":"f1515d7bd8d00201a52a7574434199fa89cd468f39c31d1597dcf2b8932ba7a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:39:56Z","title_canon_sha256":"e465d6203557af2580c234961856932e5f2a9dfa8d6934de738bd3c92fe9bcbc"},"schema_version":"1.0","source":{"id":"2505.07787","kind":"arxiv","version":1}},"canonical_sha256":"4d7848ba6d7b8e5339207cc45f7b7536054a9ee21e41c4885f21f45e2fe30b36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d7848ba6d7b8e5339207cc45f7b7536054a9ee21e41c4885f21f45e2fe30b36","first_computed_at":"2026-07-05T11:01:53.379061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:53.379061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrZ6MXiUycQtFrmDtWy0U5MCaFWIsv0J215buCaQtF21luXFSaOwX7ORotJhGGwzuBzNwwiJpeaIitz3hcOoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:53.379555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b2d48aa42989ad9ef3cefcb50b1e74fe43ac826e4ec629e093352b842b005b","sha256:0a5a68d537cba9a4ce9ef2f809634625aca86edfa82ace7f51f03f8f227c54ae"],"state_sha256":"aec725d8e768f20f1aaa056d9e87c74025a247d0114330c66715d143554a8fda"}