{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MM6TYJA6BMJX4RQMCZTYH2GN7A","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":"167cc0e1f6a7de1d49984d2042c43ba1fb601431a72982f98eb2a1d6c783bef9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T19:04:17Z","title_canon_sha256":"1ea180aefd267a8b1dde3f35378b7f05a3d1c26077b219b9bab3db1b80b685bc"},"schema_version":"1.0","source":{"id":"2507.10616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10616","created_at":"2026-07-05T11:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10616v2","created_at":"2026-07-05T11:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10616","created_at":"2026-07-05T11:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"MM6TYJA6BMJX","created_at":"2026-07-05T11:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"MM6TYJA6BMJX4RQM","created_at":"2026-07-05T11:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"MM6TYJA6","created_at":"2026-07-05T11:43:13Z"}],"graph_snapshots":[{"event_id":"sha256:80ca46ed35fe93f758ebfd8cffdb845be672a055485184db3040c08c7e3d0162","target":"graph","created_at":"2026-07-05T11:43:13Z","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/2507.10616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) for reasoning via maths and code datasets has become a major new focus in LLM post-training. Two particularly popular approaches are reinforcement learning (RL) and supervised fine-tuning (SFT), but their training dynamics are poorly understood. We present a comparative analysis of RL and SFT on the same maths problems with the same model and similar hyperparameters. We find that RL yields minor in-domain gains on maths and slight degradation on knowledge-intensive benchmarks like MMLU, while both trends are more pronounced in SFT. We also analyse model pa","authors_text":"Aryo Pradipta Gema, Ivan Titov, Neel Rajani, Seraphina Goldfarb-Tarrant","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T19:04:17Z","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10616","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":"sha256:0e22a56c0ef155911d1ff62688a88d54d63dafdd72d58c815476d27b435f1eb6","target":"record","created_at":"2026-07-05T11:43:13Z","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":"167cc0e1f6a7de1d49984d2042c43ba1fb601431a72982f98eb2a1d6c783bef9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T19:04:17Z","title_canon_sha256":"1ea180aefd267a8b1dde3f35378b7f05a3d1c26077b219b9bab3db1b80b685bc"},"schema_version":"1.0","source":{"id":"2507.10616","kind":"arxiv","version":2}},"canonical_sha256":"633d3c241e0b137e460c166783e8cdf836f617aee92c418f01bcfbd3310c7ca5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"633d3c241e0b137e460c166783e8cdf836f617aee92c418f01bcfbd3310c7ca5","first_computed_at":"2026-07-05T11:43:13.533083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:13.533083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FR+KMiHXGI292hviDDUJ5b1m88frjEPLai1Dv2z+hXsdD5U9S1iG+K3yc1Aml3iuAkhjRKZ+hvbY97UzlBUQAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:13.533549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e22a56c0ef155911d1ff62688a88d54d63dafdd72d58c815476d27b435f1eb6","sha256:80ca46ed35fe93f758ebfd8cffdb845be672a055485184db3040c08c7e3d0162"],"state_sha256":"f3237aa6afbdd3709c31d356d67136b75d31ee47bf32bfc74f054b73fc54847d"}