{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BSAZXSVB5UJMRDJ3EWNCEY2UED","short_pith_number":"pith:BSAZXSVB","schema_version":"1.0","canonical_sha256":"0c819bcaa1ed12c88d3b259a22635420f3d9968a6f16fdd6faf25d0bce761f29","source":{"kind":"arxiv","id":"2505.00913","version":1},"attestation_state":"computed","paper":{"title":"Fine-Tuning without Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Han Wang, Martha White","submitted_at":"2025-05-01T23:19:07Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.00913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T23:19:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4b6e2a134ba12c3f00157af35401f88e3e2418b7f4282dbf3932c3a9b0adf1a","abstract_canon_sha256":"ddc75dce8a6a15c7bf69cb3bd2b12bfc14eb42f189ef8997c3e03d0c183f7e05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:41.685497Z","signature_b64":"G8I4IaBBGlk1V7QFACq3QfWJAMusI5Dp9iMrhvQL8p7OotjPWg7sqZHDs54AxIMI2ZP3nHDzlrTOjTxncyZ0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c819bcaa1ed12c88d3b259a22635420f3d9968a6f16fdd6faf25d0bce761f29","last_reissued_at":"2026-07-05T10:57:41.684958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:41.684958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tuning without Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Han Wang, Martha White","submitted_at":"2025-05-01T23:19:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00913","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.00913/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.00913","created_at":"2026-07-05T10:57:41.685023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00913v1","created_at":"2026-07-05T10:57:41.685023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00913","created_at":"2026-07-05T10:57:41.685023+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSAZXSVB5UJM","created_at":"2026-07-05T10:57:41.685023+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSAZXSVB5UJMRDJ3","created_at":"2026-07-05T10:57:41.685023+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSAZXSVB","created_at":"2026-07-05T10:57:41.685023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED","json":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED.json","graph_json":"https://pith.science/api/pith-number/BSAZXSVB5UJMRDJ3EWNCEY2UED/graph.json","events_json":"https://pith.science/api/pith-number/BSAZXSVB5UJMRDJ3EWNCEY2UED/events.json","paper":"https://pith.science/paper/BSAZXSVB"},"agent_actions":{"view_html":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED","download_json":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED.json","view_paper":"https://pith.science/paper/BSAZXSVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00913&json=true","fetch_graph":"https://pith.science/api/pith-number/BSAZXSVB5UJMRDJ3EWNCEY2UED/graph.json","fetch_events":"https://pith.science/api/pith-number/BSAZXSVB5UJMRDJ3EWNCEY2UED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED/action/storage_attestation","attest_author":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED/action/author_attestation","sign_citation":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED/action/citation_signature","submit_replication":"https://pith.science/pith/BSAZXSVB5UJMRDJ3EWNCEY2UED/action/replication_record"}},"created_at":"2026-07-05T10:57:41.685023+00:00","updated_at":"2026-07-05T10:57:41.685023+00:00"}