{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BSAZXSVB5UJMRDJ3EWNCEY2UED","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":"ddc75dce8a6a15c7bf69cb3bd2b12bfc14eb42f189ef8997c3e03d0c183f7e05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T23:19:07Z","title_canon_sha256":"b4b6e2a134ba12c3f00157af35401f88e3e2418b7f4282dbf3932c3a9b0adf1a"},"schema_version":"1.0","source":{"id":"2505.00913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00913","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00913v1","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00913","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"BSAZXSVB5UJM","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"BSAZXSVB5UJMRDJ3","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"BSAZXSVB","created_at":"2026-07-05T10:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:5cb7dc925e40a513c2f99ce629a2cfee8a6db6f15aa7554b0c31722ae4daebc3","target":"graph","created_at":"2026-07-05T10:57:41Z","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/2505.00913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning policies learned offline remains a major challenge in application domains. Monotonic performance improvement during \\emph{fine-tuning} is often challenging, as agents typically experience performance degradation at the early fine-tuning stage. The community has identified multiple difficulties in fine-tuning a learned network online, however, the majority of progress has focused on improving learning efficiency during fine-tuning. In practice, this comes at a serious cost during fine-tuning: initially, agent performance degrades as the agent explores and effectively overrides the p","authors_text":"Adam White, Han Wang, Martha White","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T23:19:07Z","title":"Fine-Tuning without Performance Degradation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00913","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":"sha256:0e62c597060608d93071649e9dd41db1f014063d4f401c222097602f78151e99","target":"record","created_at":"2026-07-05T10:57:41Z","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":"ddc75dce8a6a15c7bf69cb3bd2b12bfc14eb42f189ef8997c3e03d0c183f7e05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T23:19:07Z","title_canon_sha256":"b4b6e2a134ba12c3f00157af35401f88e3e2418b7f4282dbf3932c3a9b0adf1a"},"schema_version":"1.0","source":{"id":"2505.00913","kind":"arxiv","version":1}},"canonical_sha256":"0c819bcaa1ed12c88d3b259a22635420f3d9968a6f16fdd6faf25d0bce761f29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c819bcaa1ed12c88d3b259a22635420f3d9968a6f16fdd6faf25d0bce761f29","first_computed_at":"2026-07-05T10:57:41.684958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:41.684958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G8I4IaBBGlk1V7QFACq3QfWJAMusI5Dp9iMrhvQL8p7OotjPWg7sqZHDs54AxIMI2ZP3nHDzlrTOjTxncyZ0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:41.685497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e62c597060608d93071649e9dd41db1f014063d4f401c222097602f78151e99","sha256:5cb7dc925e40a513c2f99ce629a2cfee8a6db6f15aa7554b0c31722ae4daebc3"],"state_sha256":"fa5fa500bc198758a84f339eba207dd1abc8140e46566902ef7d887bdd2d24a2"}