{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z4MPPAATJJU5JKLULCSB7Y3IK5","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":"892e4bf6ec75bc0bba3a68de1e7fe922bf119eb7606ddeb2e48cbfe8a00abb90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T16:45:31Z","title_canon_sha256":"3164ba46d12f8f82c68c059f88f9cbd049db08abca3ffdf7a36e653109a5aaab"},"schema_version":"1.0","source":{"id":"2605.22703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22703","created_at":"2026-05-22T02:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22703v1","created_at":"2026-05-22T02:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22703","created_at":"2026-05-22T02:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z4MPPAATJJU5","created_at":"2026-05-22T02:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z4MPPAATJJU5JKLU","created_at":"2026-05-22T02:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z4MPPAAT","created_at":"2026-05-22T02:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:be0a2bc173beec524c5d553a6a8d76e171a0f8dc448daf707698c62c5a71acb2","target":"graph","created_at":"2026-05-22T02:04:51Z","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/2605.22703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and suboptimal convergence. Through a systematic dissection of clipping-based GRPO-style objectives, we identify the rigid clipping decision induced by hard clipping as a key practical bottleneck in the studied RLVR setups. Specifically, our analysis suggests that informative signals can lie in the near-boundary region just beyond the clipping threshold, and are therefore discarded by the standard hard-clipping rule. Not","authors_text":"Bolin Ding, Chiyu Ma, Guoyin Wang, Haoming Meng, Jinda Lu, Jingren Zhou, Kexin Huang, Li Yuan, Qihui Zhang, Shuo Yang, Yuyang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T16:45:31Z","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22703","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":"sha256:9af25f4257ab763163f5d2c6190d286d59382ff36edfff99d3185d7ba2cdc99d","target":"record","created_at":"2026-05-22T02:04:51Z","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":"892e4bf6ec75bc0bba3a68de1e7fe922bf119eb7606ddeb2e48cbfe8a00abb90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T16:45:31Z","title_canon_sha256":"3164ba46d12f8f82c68c059f88f9cbd049db08abca3ffdf7a36e653109a5aaab"},"schema_version":"1.0","source":{"id":"2605.22703","kind":"arxiv","version":1}},"canonical_sha256":"cf18f780134a69d4a97458a41fe36857681db57b71b40dc47d17beb78155712c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf18f780134a69d4a97458a41fe36857681db57b71b40dc47d17beb78155712c","first_computed_at":"2026-05-22T02:04:51.204462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:51.204462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uq6RP8Yc8RO7NRcgszsfX5VN5JikQ4Y0/tImvq+IjBRNaNKMoL7gdxga/yjH61sDUVhntUfCvEwGptLWz+i5DQ==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:51.205302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9af25f4257ab763163f5d2c6190d286d59382ff36edfff99d3185d7ba2cdc99d","sha256:be0a2bc173beec524c5d553a6a8d76e171a0f8dc448daf707698c62c5a71acb2"],"state_sha256":"9c91b98257d53ef9b407241a8f4cfea46475690d967f2c12eb9996f09ea93f99"}