{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RYIPWZWZFDHVPJXBTBHN7NEHKF","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":"5f21879db8810a7a800e62370ac48d766bcaba7bc50967c63759a2446c401044","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:29:43Z","title_canon_sha256":"e602ce86fb22619cd2bb2015f71816355849b774e6de50a690b54a184c8e7835"},"schema_version":"1.0","source":{"id":"2606.05800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05800","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05800v1","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05800","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"RYIPWZWZFDHV","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"RYIPWZWZFDHVPJXB","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"RYIPWZWZ","created_at":"2026-06-05T01:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:02974a1eca52197db18a4e303ee962030dab62a7a3739a865376a06fc2520695","target":"graph","created_at":"2026-06-05T01:15:03Z","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/2606.05800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, causing substantial cancellation during aggregation and weakening the effective update. We address this failure mode with SALT, a Subspace-Adaptive geometry pLug-in componenT that uses sample-wise gradien","authors_text":"Chaoqun Sun, Chenyu Wang, Dongying Kong, JianXiang Xiang, Jinpeng Zhang, Lianrui Li, MiniWell Tsao, Powei Chang, Yukang Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:29:43Z","title":"SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05800","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:cdc6b0c68dd3c1d807e61574df9df4963f034e06d9e340a8828989b8e1b99d96","target":"record","created_at":"2026-06-05T01:15:03Z","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":"5f21879db8810a7a800e62370ac48d766bcaba7bc50967c63759a2446c401044","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:29:43Z","title_canon_sha256":"e602ce86fb22619cd2bb2015f71816355849b774e6de50a690b54a184c8e7835"},"schema_version":"1.0","source":{"id":"2606.05800","kind":"arxiv","version":1}},"canonical_sha256":"8e10fb66d928cf57a6e1984edfb487515c3368e3f7ec5c2cb55beed61a45b67d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e10fb66d928cf57a6e1984edfb487515c3368e3f7ec5c2cb55beed61a45b67d","first_computed_at":"2026-06-05T01:15:03.773492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:03.773492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iDfZdl8Wr8fYkSRxhn3OxTbyrVSDHUkXonBD35ngo6BaaCdXv7kVwPI2KMlbFCppz9JOBctegYyoWfqZW7KJCQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:03.774101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdc6b0c68dd3c1d807e61574df9df4963f034e06d9e340a8828989b8e1b99d96","sha256:02974a1eca52197db18a4e303ee962030dab62a7a3739a865376a06fc2520695"],"state_sha256":"a082b8ee6dc992bf7961cd23edd38c3023f905da1924457e1448e54c9a340645"}