{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGCKAJEDSGSYW5W57R5MRFYPFB","short_pith_number":"pith:JGCKAJED","schema_version":"1.0","canonical_sha256":"4984a0248391a58b76ddfc7ac8970f2874f5db8fd7743b16d121ff331c7e0fd9","source":{"kind":"arxiv","id":"2501.10979","version":2},"attestation_state":"computed","paper":{"title":"Control LLM: Controlled Evolution for Intelligence Retention in LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alice Leung, Aman Lunia, Haichao Wei, Ya Xu, Yi-Lin Chen, Yunxiang Ren, Zhoutong Fu","submitted_at":"2025-01-19T08:06:06Z","abstract_excerpt":"Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \\textit{catastrophic forgetting} (CF), which hampers performance during Continuous Pre-training (CPT) and Continuous Supervised Fine-Tuning (CSFT). We propose \\textbf{Control LLM}, a novel approach that leverages parallel pre-trained and expanded transformer blocks, aligning their hidden-states through interpolation strategies This method effectively preserves performance on existing tasks while seamlessly "},"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":"2501.10979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-19T08:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"1e8a08ab0d07c501ec41d119c6b0465b12b4587a6000dab777e35d2a08668b40","abstract_canon_sha256":"f9efd171e33afcd7d922fed357c16f198891c7d194ccf111a990f3a184ad8e52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:29.591550Z","signature_b64":"xW5NL6e8ajub7Dr7FFURLK/bZF/wzxlPocsBq5Aq88uoxAJH+N0SDpNK9CPy2liFEb8cvudjdyBlzRzQ1B9QDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4984a0248391a58b76ddfc7ac8970f2874f5db8fd7743b16d121ff331c7e0fd9","last_reissued_at":"2026-07-05T10:07:29.591084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:29.591084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control LLM: Controlled Evolution for Intelligence Retention in LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alice Leung, Aman Lunia, Haichao Wei, Ya Xu, Yi-Lin Chen, Yunxiang Ren, Zhoutong Fu","submitted_at":"2025-01-19T08:06:06Z","abstract_excerpt":"Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \\textit{catastrophic forgetting} (CF), which hampers performance during Continuous Pre-training (CPT) and Continuous Supervised Fine-Tuning (CSFT). We propose \\textbf{Control LLM}, a novel approach that leverages parallel pre-trained and expanded transformer blocks, aligning their hidden-states through interpolation strategies This method effectively preserves performance on existing tasks while seamlessly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10979","kind":"arxiv","version":2},"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/2501.10979/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":"2501.10979","created_at":"2026-07-05T10:07:29.591141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10979v2","created_at":"2026-07-05T10:07:29.591141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10979","created_at":"2026-07-05T10:07:29.591141+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGCKAJEDSGSY","created_at":"2026-07-05T10:07:29.591141+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGCKAJEDSGSYW5W5","created_at":"2026-07-05T10:07:29.591141+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGCKAJED","created_at":"2026-07-05T10:07:29.591141+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/JGCKAJEDSGSYW5W57R5MRFYPFB","json":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB.json","graph_json":"https://pith.science/api/pith-number/JGCKAJEDSGSYW5W57R5MRFYPFB/graph.json","events_json":"https://pith.science/api/pith-number/JGCKAJEDSGSYW5W57R5MRFYPFB/events.json","paper":"https://pith.science/paper/JGCKAJED"},"agent_actions":{"view_html":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB","download_json":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB.json","view_paper":"https://pith.science/paper/JGCKAJED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10979&json=true","fetch_graph":"https://pith.science/api/pith-number/JGCKAJEDSGSYW5W57R5MRFYPFB/graph.json","fetch_events":"https://pith.science/api/pith-number/JGCKAJEDSGSYW5W57R5MRFYPFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB/action/storage_attestation","attest_author":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB/action/author_attestation","sign_citation":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB/action/citation_signature","submit_replication":"https://pith.science/pith/JGCKAJEDSGSYW5W57R5MRFYPFB/action/replication_record"}},"created_at":"2026-07-05T10:07:29.591141+00:00","updated_at":"2026-07-05T10:07:29.591141+00:00"}