{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VFFGSMULKVLBK65A4UZ25TY23R","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":"231ba2bb3b0cf8dbf57fef77d63342f80eb7d9bf62769de73bbd744da7b24787","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T21:47:31Z","title_canon_sha256":"039fea9f6290d9123d1069bd4df344b2a2e06231f7f5f1516c441d36108dd921"},"schema_version":"1.0","source":{"id":"2606.08854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08854","created_at":"2026-06-09T02:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08854v1","created_at":"2026-06-09T02:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08854","created_at":"2026-06-09T02:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"VFFGSMULKVLB","created_at":"2026-06-09T02:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"VFFGSMULKVLBK65A","created_at":"2026-06-09T02:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"VFFGSMUL","created_at":"2026-06-09T02:07:43Z"}],"graph_snapshots":[{"event_id":"sha256:2bb08fdfb16d12bcc4994dc18f50c907a15112fc1582f48b0f61866bce79840c","target":"graph","created_at":"2026-06-09T02:07:43Z","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/2606.08854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy. This leads to two symmetric failure modes: easy queries produce near-zero advantage because the policy already solves them, while unsolvable queries produce no signal because the policy never solves them. Both regimes waste training FLOPs without contributing to a learning gradient. We introduce sorted Group Policy Optimization (sGPO), a compute-efficient strategy that trades a small budget of infe","authors_text":"Akash Srivastava, Giorgio Giannone, Kai Xu, Shivchander Sudalairaj","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T21:47:31Z","title":"sGPO: Trading Inference FLOPs for Training Efficiency in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08854","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:e45b69821b5531b049f47163fcc869e2339731869f3305cd3e2403dc8c20139b","target":"record","created_at":"2026-06-09T02:07:43Z","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":"231ba2bb3b0cf8dbf57fef77d63342f80eb7d9bf62769de73bbd744da7b24787","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T21:47:31Z","title_canon_sha256":"039fea9f6290d9123d1069bd4df344b2a2e06231f7f5f1516c441d36108dd921"},"schema_version":"1.0","source":{"id":"2606.08854","kind":"arxiv","version":1}},"canonical_sha256":"a94a69328b5556157ba0e533aecf1adc7b51c1e6b9c581f68cf55124803ed2ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a94a69328b5556157ba0e533aecf1adc7b51c1e6b9c581f68cf55124803ed2ab","first_computed_at":"2026-06-09T02:07:43.036065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:43.036065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WrmAUhXs/o8Fh71/Dz+QuzetLtP5GoqAJJFtzNYtgaNm+eKKV/Uq5RjSQrOglmbQtSgjvZd9QGKraYbQxKeTDw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:43.036959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e45b69821b5531b049f47163fcc869e2339731869f3305cd3e2403dc8c20139b","sha256:2bb08fdfb16d12bcc4994dc18f50c907a15112fc1582f48b0f61866bce79840c"],"state_sha256":"26f58a1fae127cce18c01a4c3904b4a97229996fe8632f2a757a8e0c268ed4dc"}