{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6FXKHXSJD5OKIOZ2Y26N6UXQ4Z","short_pith_number":"pith:6FXKHXSJ","schema_version":"1.0","canonical_sha256":"f16ea3de491f5ca43b3ac6bcdf52f0e6776347e29b2efd56f9f8fffd0b4b0de2","source":{"kind":"arxiv","id":"2305.02279","version":3},"attestation_state":"computed","paper":{"title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jing Wang, Qiufeng Wang, Shuxia Lin, Xin Geng, Xu Yang","submitted_at":"2023-05-03T17:15:58Z","abstract_excerpt":"During the continuous evolution of one organism's ancestry, its genes accumulate extensive experiences and knowledge, enabling newborn descendants to rapidly adapt to their specific environments. Motivated by this observation, we propose a novel machine learning paradigm Learngene to enable learning models to incorporate three key characteristics of genes. (i) Accumulating: the knowledge is accumulated during the continuous learning of an ancestry model. (ii) Condensing: the extensive accumulated knowledge is condensed into a much more compact information piece, i.e., learngene. (iii) Inheriti"},"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":"2305.02279","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:15:58Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0d112451190e63783de7a1869fb01c922f966c4dae8a358a6db939bee83bb55f","abstract_canon_sha256":"76756dd6c6f69b1705a79b4dfc756dae738cf01dd63c2f272799aac249d9da12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:02.146861Z","signature_b64":"DV4Lt/UidBb86ndit1uaUh/Nr2UGyEX5Mc/Ze/SKMkSC8HjKgz1Ymrzp9pu5Ke8OKKGcyfqUhY8DY3M8s0HFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16ea3de491f5ca43b3ac6bcdf52f0e6776347e29b2efd56f9f8fffd0b4b0de2","last_reissued_at":"2026-07-05T06:26:02.146349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:02.146349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jing Wang, Qiufeng Wang, Shuxia Lin, Xin Geng, Xu Yang","submitted_at":"2023-05-03T17:15:58Z","abstract_excerpt":"During the continuous evolution of one organism's ancestry, its genes accumulate extensive experiences and knowledge, enabling newborn descendants to rapidly adapt to their specific environments. Motivated by this observation, we propose a novel machine learning paradigm Learngene to enable learning models to incorporate three key characteristics of genes. (i) Accumulating: the knowledge is accumulated during the continuous learning of an ancestry model. (ii) Condensing: the extensive accumulated knowledge is condensed into a much more compact information piece, i.e., learngene. (iii) Inheriti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02279","kind":"arxiv","version":3},"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/2305.02279/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":"2305.02279","created_at":"2026-07-05T06:26:02.146408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02279v3","created_at":"2026-07-05T06:26:02.146408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02279","created_at":"2026-07-05T06:26:02.146408+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FXKHXSJD5OK","created_at":"2026-07-05T06:26:02.146408+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FXKHXSJD5OKIOZ2","created_at":"2026-07-05T06:26:02.146408+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FXKHXSJ","created_at":"2026-07-05T06:26:02.146408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06519","citing_title":"SafeGene: Reusable Adapters for Transferable Safety Alignment","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08209","citing_title":"Learngene Search Across Multiple Datasets for Building Variable-Sized Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08842","citing_title":"XPERT: Expert Knowledge Transfer for Effective Training of Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07783","citing_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","ref_index":100,"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":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14769","citing_title":"Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z","json":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z.json","graph_json":"https://pith.science/api/pith-number/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/graph.json","events_json":"https://pith.science/api/pith-number/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/events.json","paper":"https://pith.science/paper/6FXKHXSJ"},"agent_actions":{"view_html":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z","download_json":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z.json","view_paper":"https://pith.science/paper/6FXKHXSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02279&json=true","fetch_graph":"https://pith.science/api/pith-number/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/action/storage_attestation","attest_author":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/action/author_attestation","sign_citation":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/action/citation_signature","submit_replication":"https://pith.science/pith/6FXKHXSJD5OKIOZ2Y26N6UXQ4Z/action/replication_record"}},"created_at":"2026-07-05T06:26:02.146408+00:00","updated_at":"2026-07-05T06:26:02.146408+00:00"}