{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OK2RXQX3XKQ6ZRI6M67WOX4EG6","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":"90748e18964bf29367a1c0d6b9bf65cd4711903e1ddbe9b8dd1467df5f47be4e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T17:59:41Z","title_canon_sha256":"406089db1e4544235f91fc7037237ae80de52a121f27e8395111d62d0a2f610e"},"schema_version":"1.0","source":{"id":"2510.18874","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.18874","created_at":"2026-06-29T01:14:25Z"},{"alias_kind":"arxiv_version","alias_value":"2510.18874v3","created_at":"2026-06-29T01:14:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18874","created_at":"2026-06-29T01:14:25Z"},{"alias_kind":"pith_short_12","alias_value":"OK2RXQX3XKQ6","created_at":"2026-06-29T01:14:25Z"},{"alias_kind":"pith_short_16","alias_value":"OK2RXQX3XKQ6ZRI6","created_at":"2026-06-29T01:14:25Z"},{"alias_kind":"pith_short_8","alias_value":"OK2RXQX3","created_at":"2026-06-29T01:14:25Z"}],"graph_snapshots":[{"event_id":"sha256:21a1b623d4f3a5169e4ccbc38dd6d7f3d495ab6a2c9bb6773e531fab538b5351","target":"graph","created_at":"2026-06-29T01:14:25Z","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/2510.18874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this phenomenon, we systematically compare the forgetting patterns of two widely adopted post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL). Our experiments reveal a consistent trend across LM families (Llama, Qwen) and tasks (instruction following, general knowledge, and arithmetic reasoning): RL leads to less forgetting than SF","authors_text":"Danqi Chen, Howard Chen, Karthik Narasimhan, Noam Razin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T17:59:41Z","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18874","kind":"arxiv","version":3},"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":"sha256:40d5b2ac254f746e62430b8d2c807f2d4d3299e7bf2ff191c6f85093c990ff0f","target":"record","created_at":"2026-06-29T01:14:25Z","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":"90748e18964bf29367a1c0d6b9bf65cd4711903e1ddbe9b8dd1467df5f47be4e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T17:59:41Z","title_canon_sha256":"406089db1e4544235f91fc7037237ae80de52a121f27e8395111d62d0a2f610e"},"schema_version":"1.0","source":{"id":"2510.18874","kind":"arxiv","version":3}},"canonical_sha256":"72b51bc2fbbaa1ecc51e67bf675f8437bf01f0b8eedc70abd7ee8dd515130274","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72b51bc2fbbaa1ecc51e67bf675f8437bf01f0b8eedc70abd7ee8dd515130274","first_computed_at":"2026-06-29T01:14:25.141813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:25.141813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"izpt6DUTe0riw14TGgiYN5LUUnkWU9C66f+8UuE8yDPbWs1d/bapXdA7bn8Sdd7zIUJaIAOsJX9AjIX9MB1gBQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:25.142370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.18874","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40d5b2ac254f746e62430b8d2c807f2d4d3299e7bf2ff191c6f85093c990ff0f","sha256:21a1b623d4f3a5169e4ccbc38dd6d7f3d495ab6a2c9bb6773e531fab538b5351"],"state_sha256":"4ff75dc0d920ecca3f33aca552dc01bce3ed0b12025783f26e6506a7b6e9fedf"}