{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W7TZCUD5CUHQBLBHSIRHHGAFO5","short_pith_number":"pith:W7TZCUD5","schema_version":"1.0","canonical_sha256":"b7e791507d150f00ac27922273980577732af19f2291fc104ac0560e8383ffd5","source":{"kind":"arxiv","id":"2506.16673","version":1},"attestation_state":"computed","paper":{"title":"Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Junming Yang, Ruiming Chen, Shiyu Xia, Xin Geng, Xu Yang","submitted_at":"2025-06-20T01:17:41Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, the computational overhead of a large number of parameters and large-scale pre-training poses challenges of pre-training a different scale of CLIP. Learngene extracts the generalizable components termed as learngene from an ancestry model and initializes diverse descendant models with it. Previous Learngene paradigms fail to handle the generalizable knowledge in multimodal scenarios. In this paper, we put forward the i"},"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":"2506.16673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"6dba6ff6909ab475c5f99b97d65db17ee642b0bf7511fa2c8da4b11483067ef6","abstract_canon_sha256":"5272cac10a3d1eae3ff83657934b4dd67719553a35b5ada530dcfffd4d6b28a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:40.514211Z","signature_b64":"Gfox5TyL/CWk3vcpZwzFQYF0C+bbyfYj2MbT27YIjJ1b29eouLceWNK+Z8UTfZhyslbn6WTIxYBrd+6Mxot0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7e791507d150f00ac27922273980577732af19f2291fc104ac0560e8383ffd5","last_reissued_at":"2026-07-05T11:24:40.513696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:40.513696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Junming Yang, Ruiming Chen, Shiyu Xia, Xin Geng, Xu Yang","submitted_at":"2025-06-20T01:17:41Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, the computational overhead of a large number of parameters and large-scale pre-training poses challenges of pre-training a different scale of CLIP. Learngene extracts the generalizable components termed as learngene from an ancestry model and initializes diverse descendant models with it. Previous Learngene paradigms fail to handle the generalizable knowledge in multimodal scenarios. In this paper, we put forward the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16673","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/2506.16673/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":"2506.16673","created_at":"2026-07-05T11:24:40.513759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16673v1","created_at":"2026-07-05T11:24:40.513759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16673","created_at":"2026-07-05T11:24:40.513759+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7TZCUD5CUHQ","created_at":"2026-07-05T11:24:40.513759+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7TZCUD5CUHQBLBH","created_at":"2026-07-05T11:24:40.513759+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7TZCUD5","created_at":"2026-07-05T11:24:40.513759+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":30,"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":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5","json":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5.json","graph_json":"https://pith.science/api/pith-number/W7TZCUD5CUHQBLBHSIRHHGAFO5/graph.json","events_json":"https://pith.science/api/pith-number/W7TZCUD5CUHQBLBHSIRHHGAFO5/events.json","paper":"https://pith.science/paper/W7TZCUD5"},"agent_actions":{"view_html":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5","download_json":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5.json","view_paper":"https://pith.science/paper/W7TZCUD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16673&json=true","fetch_graph":"https://pith.science/api/pith-number/W7TZCUD5CUHQBLBHSIRHHGAFO5/graph.json","fetch_events":"https://pith.science/api/pith-number/W7TZCUD5CUHQBLBHSIRHHGAFO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5/action/storage_attestation","attest_author":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5/action/author_attestation","sign_citation":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5/action/citation_signature","submit_replication":"https://pith.science/pith/W7TZCUD5CUHQBLBHSIRHHGAFO5/action/replication_record"}},"created_at":"2026-07-05T11:24:40.513759+00:00","updated_at":"2026-07-05T11:24:40.513759+00:00"}