{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E2ZOQ5GKF72AVQYZ6TIKDONNBP","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":"e8e8a852f01679b31e624190eae17bd2278c199e3297bd2db3b1b2a35a5896fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T11:04:31Z","title_canon_sha256":"e204f5b8e4758b1323bb51a03ba29b9d9989e5b35420eaa4ee001a344d2518d7"},"schema_version":"1.0","source":{"id":"2605.18851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18851","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18851v1","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18851","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"E2ZOQ5GKF72A","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"E2ZOQ5GKF72AVQYZ","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"E2ZOQ5GK","created_at":"2026-05-20T00:06:25Z"}],"graph_snapshots":[{"event_id":"sha256:8283199b367689dc326ee33a5c15e38c61484b18a3a7cf343baa3f1642032440","target":"graph","created_at":"2026-05-20T00:06:25Z","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/2605.18851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain coverage, while scalar scores further impose an information bottleneck, offering insufficient semantic bandwidth to improve intermediate decisions. Alternative language-critique approaches, which rely on frozen or external critics, provide richer textual feedback but lack the scalability needed for sustained policy improvement. In this work, we propose languag","authors_text":"Dacheng Tao, Guozheng Ma, Junjie Zhang, Shunyu Liu, Ting-En Lin, Yongbin Li, Yongcheng Jing, Zetian Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T11:04:31Z","title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18851","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:d7468fc4500d851f5a6c028e4042dcce90a6da082c91eef98a1eb2d6eafada7e","target":"record","created_at":"2026-05-20T00:06:25Z","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":"e8e8a852f01679b31e624190eae17bd2278c199e3297bd2db3b1b2a35a5896fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T11:04:31Z","title_canon_sha256":"e204f5b8e4758b1323bb51a03ba29b9d9989e5b35420eaa4ee001a344d2518d7"},"schema_version":"1.0","source":{"id":"2605.18851","kind":"arxiv","version":1}},"canonical_sha256":"26b2e874ca2ff40ac319f4d0a1b9ad0bd790a5dc4eacfe69c482e135297a2951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b2e874ca2ff40ac319f4d0a1b9ad0bd790a5dc4eacfe69c482e135297a2951","first_computed_at":"2026-05-20T00:06:25.691799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:25.691799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PaR3l74oPmYqnJwXHkbVlQhklFtva+MaNbQ7hXf4wdF6OklMYrHYr6IDtCFkTBnJa1DzE1v5qxUQLhBsuuD6DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:25.692578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7468fc4500d851f5a6c028e4042dcce90a6da082c91eef98a1eb2d6eafada7e","sha256:8283199b367689dc326ee33a5c15e38c61484b18a3a7cf343baa3f1642032440"],"state_sha256":"c804d046ec71eeafdaf517417d6d619df8b8ec3ac38a6e0c7eea6bc27c9d4ec8"}