{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHAVRVZFRHPXZWCD5G7OLUSV26","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":"7afa869029282f14689b1e12f2c495207340c78cd61e3345759d3e71ca739d28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T17:15:12Z","title_canon_sha256":"48fe5685bf33dce4f8533a249f14fdb33a96f569bafa0be200e320e546dbddb3"},"schema_version":"1.0","source":{"id":"2602.05897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.05897","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2602.05897v2","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05897","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"GHAVRVZFRHPX","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"GHAVRVZFRHPXZWCD","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"GHAVRVZF","created_at":"2026-05-28T01:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:41f627c9eb95fc75f6ffa0ecb20954e960f61db8e6bbf9a1a85466ee1cb47fd9","target":"graph","created_at":"2026-05-28T01:04:36Z","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/2602.05897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings. However, they are prone to faithfulness hallucinations, especially in intermediate reasoning steps. Existing mitigation methods based on online reinforcement learning rely on outcome-based rewards or coarse-grained CoT evaluation, which can inadvertently reinforce unfaithful reasoning when the final answer is correct. To address these limitations, we propose Faithfulness-Aware Step-Level Reinforcement Learning (Fai","authors_text":"Chao Wang, Hexuan Deng, Min Zhang, Ruiyu Fang, Shuangyong Song, Shuo Nie, Xuebo Liu, Xuelong Li, Yu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T17:15:12Z","title":"Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05897","kind":"arxiv","version":2},"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":"sha256:2f4ca0c3ad2c6781d8a5bd6ba083621766e892301c2778d039c3855d9f346cb9","target":"record","created_at":"2026-05-28T01:04:36Z","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":"7afa869029282f14689b1e12f2c495207340c78cd61e3345759d3e71ca739d28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T17:15:12Z","title_canon_sha256":"48fe5685bf33dce4f8533a249f14fdb33a96f569bafa0be200e320e546dbddb3"},"schema_version":"1.0","source":{"id":"2602.05897","kind":"arxiv","version":2}},"canonical_sha256":"31c158d72589df7cd843e9bee5d255d7ba1eaf21749dfe79ebe22c32118a2256","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31c158d72589df7cd843e9bee5d255d7ba1eaf21749dfe79ebe22c32118a2256","first_computed_at":"2026-05-28T01:04:36.452046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:36.452046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNo7dRYTZWULPjqVkdYTkl2CGDs580hbrEcy0FbO3siZ2sSzJr20dukUw1Gfn7vHjvoTJfKVTGIcLWFgogagCA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:36.452574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.05897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f4ca0c3ad2c6781d8a5bd6ba083621766e892301c2778d039c3855d9f346cb9","sha256:41f627c9eb95fc75f6ffa0ecb20954e960f61db8e6bbf9a1a85466ee1cb47fd9"],"state_sha256":"422d8599124e3f547c2c17fd02425617ce16eab96b0956b25c2a4ab2fa135907"}