{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NBSTXQN4XVAB7LB7AL6TSKM7AU","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":"02de09453dd20d24c85b32f63c9f20a328a07a208c94e8129c90148e01f83bae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T01:02:17Z","title_canon_sha256":"d80c336febb51f6e4d0229c28d38c9cb3d32cb52f65d9faf7c4d78e659d157fe"},"schema_version":"1.0","source":{"id":"2507.17107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17107","created_at":"2026-07-05T11:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17107v2","created_at":"2026-07-05T11:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17107","created_at":"2026-07-05T11:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"NBSTXQN4XVAB","created_at":"2026-07-05T11:44:52Z"},{"alias_kind":"pith_short_16","alias_value":"NBSTXQN4XVAB7LB7","created_at":"2026-07-05T11:44:52Z"},{"alias_kind":"pith_short_8","alias_value":"NBSTXQN4","created_at":"2026-07-05T11:44:52Z"}],"graph_snapshots":[{"event_id":"sha256:1276ad75ab3ed20be442152fe4f3c71a25e5ca65d72414d2af526938d0bcf93a","target":"graph","created_at":"2026-07-05T11:44:52Z","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/2507.17107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we challenge this assumption with a surprising finding: RL fine-tuning consistently modifies only a small subnetwork (typically 5-30% of weights), leaving most parameters unchanged. We call this phenomenon RL-induced parameter update sparsity. It arises naturally, without any sparsity constraints or parameter-efficient tuning, and appears across multiple RL alg","authors_text":"Andrii Balashov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T01:02:17Z","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17107","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:a0bb66bb12179cdcde4460aa910db2167660710ffdbc3bbbaaa56bd451a705c7","target":"record","created_at":"2026-07-05T11:44:52Z","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":"02de09453dd20d24c85b32f63c9f20a328a07a208c94e8129c90148e01f83bae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T01:02:17Z","title_canon_sha256":"d80c336febb51f6e4d0229c28d38c9cb3d32cb52f65d9faf7c4d78e659d157fe"},"schema_version":"1.0","source":{"id":"2507.17107","kind":"arxiv","version":2}},"canonical_sha256":"68653bc1bcbd401fac3f02fd39299f0526c60be074053abb8825498f40c774c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68653bc1bcbd401fac3f02fd39299f0526c60be074053abb8825498f40c774c8","first_computed_at":"2026-07-05T11:44:52.182768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:52.182768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AHEMNM1HDI7P7TxIB8R425kxDEixYOpf63lNwytPs4cWZQWzuBE9NcpdO/EvhVQKWZomHmIeR0BKO2KdL6JoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:52.183250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0bb66bb12179cdcde4460aa910db2167660710ffdbc3bbbaaa56bd451a705c7","sha256:1276ad75ab3ed20be442152fe4f3c71a25e5ca65d72414d2af526938d0bcf93a"],"state_sha256":"ce3848099a99f99c9104a9ea70c349862d13c29002f6de3ba5010683017602ac"}