{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NWOPEFVBXJ5QRMEB5U2JNXP6VT","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":"1c04c650fa271179d7c01f2932c5bc6126e608396c54fccd94cc7ac420079dbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T08:27:15Z","title_canon_sha256":"1cee7d3be23b20fb83955e127cd12daa2b42a1b56f6574ca59d2fc7096c32f2a"},"schema_version":"1.0","source":{"id":"2608.09271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09271","created_at":"2026-08-11T02:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09271v1","created_at":"2026-08-11T02:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09271","created_at":"2026-08-11T02:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"NWOPEFVBXJ5Q","created_at":"2026-08-11T02:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"NWOPEFVBXJ5QRMEB","created_at":"2026-08-11T02:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"NWOPEFVB","created_at":"2026-08-11T02:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:1e4a35d0fb28f55fa722a60e319a4f09554680e7321596353800b36bcd8a69e1","target":"graph","created_at":"2026-08-11T02:22:13Z","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/2608.09271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-based reinforcement learning objectives such as GRPO can allocate learning signal poorly across prompt difficulty: under binary rewards, group normalization induces a divergent weighting on easy prompts. We introduce Softmax Advantage Group Estimation (SoftmaxGRPO), a drop-in alternative that replaces z-score-normalized group advantages with temperature-scaled softmax advantages, keeping weights bounded regardless of prompt difficulty. For binary rewards, we derive the exact finite-group population objective and identify MaxRL as its low-temperature limit. For bounded scalar rewards, we ","authors_text":"Chen Wei, Jaywon Koo, Jefferson Hernandez, Vicente Ordonez, Zilin Xiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T08:27:15Z","title":"SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09271","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":"sha256:3582d40ae8ac8746822b879d07b3bdcfc4c4b66251e077d1840acaac3aab2257","target":"record","created_at":"2026-08-11T02:22:13Z","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":"1c04c650fa271179d7c01f2932c5bc6126e608396c54fccd94cc7ac420079dbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T08:27:15Z","title_canon_sha256":"1cee7d3be23b20fb83955e127cd12daa2b42a1b56f6574ca59d2fc7096c32f2a"},"schema_version":"1.0","source":{"id":"2608.09271","kind":"arxiv","version":1}},"canonical_sha256":"6d9cf216a1ba7b08b081ed3496ddfeacf8407e65a0e432382829e79d428ff7b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d9cf216a1ba7b08b081ed3496ddfeacf8407e65a0e432382829e79d428ff7b9","first_computed_at":"2026-08-11T02:22:13.309017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:13.309017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wRoXN9LvugNP6RWQNV+JTHmMW3oG+g3iWIKFa41kw8F57HZPC45eSv/ODrbhJBjvwOu3CdS1EbNLNkCm2BnvAw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:13.310640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3582d40ae8ac8746822b879d07b3bdcfc4c4b66251e077d1840acaac3aab2257","sha256:1e4a35d0fb28f55fa722a60e319a4f09554680e7321596353800b36bcd8a69e1"],"state_sha256":"e6cd1b38fb27c3bdc553fa470272e3748e319082d4232a0ce0d14d7aecf38c63"}