{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XKB76IJKJS464ULME7OLT2RTM2","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":"c21ee5f1d411588d3d65e2ee4249eacb17d11ec450ef8b92f9212be5ad3383de","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T10:48:02Z","title_canon_sha256":"e1b4eb71ca227ad51de8f75cc8e6f63a2c73dc9892cca58185aba5f4aec51732"},"schema_version":"1.0","source":{"id":"2601.07408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.07408","created_at":"2026-06-04T01:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2601.07408v2","created_at":"2026-06-04T01:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07408","created_at":"2026-06-04T01:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"XKB76IJKJS46","created_at":"2026-06-04T01:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"XKB76IJKJS464ULM","created_at":"2026-06-04T01:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"XKB76IJK","created_at":"2026-06-04T01:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:c154130167a55f4d3bb034036f4eb621dd6e47e65325613b10d95ada74e2875b","target":"graph","created_at":"2026-06-04T01:08:39Z","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/2601.07408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. We address this limitation by introducing Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model's final answer. We instantiate OAR ","authors_text":"Deqing Yang, Feng Xiao, Hongcheng Guo, Liu Kang, Luxi Xing, Qingyi Si, Weikang Gong, Yanghua Xiao, Zhuoran Li, Ziheng Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T10:48:02Z","title":"Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07408","kind":"arxiv","version":2},"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:cdc6c995ab90c28aced2f9c707bc2c23600959f2e98f936bd996c5502e5135d2","target":"record","created_at":"2026-06-04T01:08:39Z","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":"c21ee5f1d411588d3d65e2ee4249eacb17d11ec450ef8b92f9212be5ad3383de","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T10:48:02Z","title_canon_sha256":"e1b4eb71ca227ad51de8f75cc8e6f63a2c73dc9892cca58185aba5f4aec51732"},"schema_version":"1.0","source":{"id":"2601.07408","kind":"arxiv","version":2}},"canonical_sha256":"ba83ff212a4cb9ee516c27dcb9ea3366837e58ae8f70076a7f4c7e7c270cfec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba83ff212a4cb9ee516c27dcb9ea3366837e58ae8f70076a7f4c7e7c270cfec4","first_computed_at":"2026-06-04T01:08:39.736778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:39.736778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JE++Q0hupVpNhg7rqJnLWMSDpznWLtS1xtCAvvJMe+52/9msK7HuC5uBV/Ta0LVmBBc7X0k2dS04+Hq0odkeAw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:39.737639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.07408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdc6c995ab90c28aced2f9c707bc2c23600959f2e98f936bd996c5502e5135d2","sha256:c154130167a55f4d3bb034036f4eb621dd6e47e65325613b10d95ada74e2875b"],"state_sha256":"9aacf2df2a282f71083e9652c30967b99fad8ae7c7e1b7077433ff1cf0ca7b44"}