{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAJ6CHL3JRGKDHZ43UI5FJ57CQ","short_pith_number":"pith:BAJ6CHL3","schema_version":"1.0","canonical_sha256":"0813e11d7b4c4ca19f3cdd11d2a7bf1420f95a146667be636ea9848ff1a381fa","source":{"kind":"arxiv","id":"2401.08139","version":1},"attestation_state":"computed","paper":{"title":"Transferring Core Knowledge via Learngenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Fu Feng, Jing Wang, Xin Geng","submitted_at":"2024-01-16T06:18:11Z","abstract_excerpt":"The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary, which may lead to negative transfer. In comparison, knowledge transfer in nature is much more efficient. When passing genetic information to descendants, ancestors encode only the essential knowledge into genes, which act as the medium. Inspired by that, we adopt a recent concept called ``learngene'' and refine its structures by mimicking the structures of natu"},"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":"2401.08139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-16T06:18:11Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"afce70ec2153905fa936b51c5d2fd921f38d96b1fb2388be5897de33b3322f2d","abstract_canon_sha256":"c5dc5a1e6647d33d09ed7d17a2b648194044bfde0867655830e5abc2e04e2a5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:07.953254Z","signature_b64":"pbfMNDrq1Mm8jLsrhaO01oWlXXrSZDjb5XN5DVUANqE9SF6NcCIp2gNvDBp42oGh0rfu8lJmcxRMlkQ3mDD1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0813e11d7b4c4ca19f3cdd11d2a7bf1420f95a146667be636ea9848ff1a381fa","last_reissued_at":"2026-07-05T07:34:07.952790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:07.952790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Core Knowledge via Learngenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Fu Feng, Jing Wang, Xin Geng","submitted_at":"2024-01-16T06:18:11Z","abstract_excerpt":"The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary, which may lead to negative transfer. In comparison, knowledge transfer in nature is much more efficient. When passing genetic information to descendants, ancestors encode only the essential knowledge into genes, which act as the medium. Inspired by that, we adopt a recent concept called ``learngene'' and refine its structures by mimicking the structures of natu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08139","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/2401.08139/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":"2401.08139","created_at":"2026-07-05T07:34:07.952869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08139v1","created_at":"2026-07-05T07:34:07.952869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08139","created_at":"2026-07-05T07:34:07.952869+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAJ6CHL3JRGK","created_at":"2026-07-05T07:34:07.952869+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAJ6CHL3JRGKDHZ4","created_at":"2026-07-05T07:34:07.952869+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAJ6CHL3","created_at":"2026-07-05T07:34:07.952869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07783","citing_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07271","citing_title":"Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ","json":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ.json","graph_json":"https://pith.science/api/pith-number/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/graph.json","events_json":"https://pith.science/api/pith-number/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/events.json","paper":"https://pith.science/paper/BAJ6CHL3"},"agent_actions":{"view_html":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ","download_json":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ.json","view_paper":"https://pith.science/paper/BAJ6CHL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08139&json=true","fetch_graph":"https://pith.science/api/pith-number/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/action/storage_attestation","attest_author":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/action/author_attestation","sign_citation":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/action/citation_signature","submit_replication":"https://pith.science/pith/BAJ6CHL3JRGKDHZ43UI5FJ57CQ/action/replication_record"}},"created_at":"2026-07-05T07:34:07.952869+00:00","updated_at":"2026-07-05T07:34:07.952869+00:00"}