{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KZWMQ6ZCSHPAJFEZENQT3YJSDU","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":"7071725cc6d821357e5e666e6d523658e9ff6ce3d2bd390cdb81fe11b6fed664","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T17:51:06Z","title_canon_sha256":"b990ed007b06d871a93856b91699ac10e60786532f4781394de2130d67a631fe"},"schema_version":"1.0","source":{"id":"2507.02841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02841","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02841v1","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02841","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"KZWMQ6ZCSHPA","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"KZWMQ6ZCSHPAJFEZ","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"KZWMQ6ZC","created_at":"2026-07-05T11:31:35Z"}],"graph_snapshots":[{"event_id":"sha256:7906fd3d301d15f7bb9e0e04753981c8df45a52035798ae2867c1bfa5ad81e08","target":"graph","created_at":"2026-07-05T11:31:35Z","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/2507.02841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward problem, where a small mistake can invalidate an otherwise correct reasoning process, greatly hindering training efficiency; and exploration stagnation, where models tend to focus on solutions within their ``comfort zone,'' lacking the motivation to explore potentially more effective alternatives. To address these challenges, we propose StepHint, a novel RL","authors_text":"Ang Lv, Feng Wang, Haoyuan Hu, Jinpeng Li, Kaiyi Zhang, Rui Yan, Yongbo Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T17:51:06Z","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02841","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":"sha256:0da5fae8c3aec00051b446975cdef919ebcef63770c45583bf8eba49be585848","target":"record","created_at":"2026-07-05T11:31:35Z","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":"7071725cc6d821357e5e666e6d523658e9ff6ce3d2bd390cdb81fe11b6fed664","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T17:51:06Z","title_canon_sha256":"b990ed007b06d871a93856b91699ac10e60786532f4781394de2130d67a631fe"},"schema_version":"1.0","source":{"id":"2507.02841","kind":"arxiv","version":1}},"canonical_sha256":"566cc87b2291de04949923613de1321d349f1615077dad308bb42856cdc22a33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"566cc87b2291de04949923613de1321d349f1615077dad308bb42856cdc22a33","first_computed_at":"2026-07-05T11:31:35.236895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:35.236895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sHvgArx7E/t9LDDKZ+3wEALSeizLZS4Kjk8uq56SkbH31255zAGHPRyrcihhCEBiOLwNL/Mom5HTHRnginBoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:35.237416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0da5fae8c3aec00051b446975cdef919ebcef63770c45583bf8eba49be585848","sha256:7906fd3d301d15f7bb9e0e04753981c8df45a52035798ae2867c1bfa5ad81e08"],"state_sha256":"4fa9f4e9929d830fa4a1ba5a73518e43a0cd2eb0be8c3309f9edf43370070edb"}