{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVQDF24ESRKU6DOROP4XAURNPO","short_pith_number":"pith:MVQDF24E","schema_version":"1.0","canonical_sha256":"656032eb8494554f0dd173f970522d7bb635c7e63b2d240845df7b8c557a1274","source":{"kind":"arxiv","id":"2406.09003","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Chengwei Zhu, Jingxuan Kang, Lincan Cai, Shuang Li, Wenxuan Ma, Zixun Sun","submitted_at":"2024-06-13T11:12:46Z","abstract_excerpt":"Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses challenges due to the significant modality discrepancy and scarcity of labeled data. In this paper, we propose an end-to-end method, PaRe, to enhance cross-modal fine-tuning, aiming to transfer a large-scale pretrained model to various target modalities. PaRe employs a gating mechanism to select key patches from both source and target data. Through a modality-a"},"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":"2406.09003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T11:12:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78ffb7d9e03a3af0f5a2a49ab2e9291500a274d16df1f62984547286a9100562","abstract_canon_sha256":"9047ace382ce253ed61ead898ca566c624d29526f6be5ec699bd22f43f082cf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:27.024677Z","signature_b64":"hamcG41oTPciOVcFmhrl0RiXN6l/OWye0InRso6NUwH+Kq2LhTBzCM2zLXNPR7IPpFSkwidi4S7XXjLSaOiJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656032eb8494554f0dd173f970522d7bb635c7e63b2d240845df7b8c557a1274","last_reissued_at":"2026-07-05T08:31:27.024220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:27.024220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Chengwei Zhu, Jingxuan Kang, Lincan Cai, Shuang Li, Wenxuan Ma, Zixun Sun","submitted_at":"2024-06-13T11:12:46Z","abstract_excerpt":"Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses challenges due to the significant modality discrepancy and scarcity of labeled data. In this paper, we propose an end-to-end method, PaRe, to enhance cross-modal fine-tuning, aiming to transfer a large-scale pretrained model to various target modalities. PaRe employs a gating mechanism to select key patches from both source and target data. Through a modality-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09003","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/2406.09003/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":"2406.09003","created_at":"2026-07-05T08:31:27.024273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09003v1","created_at":"2026-07-05T08:31:27.024273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09003","created_at":"2026-07-05T08:31:27.024273+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVQDF24ESRKU","created_at":"2026-07-05T08:31:27.024273+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVQDF24ESRKU6DOR","created_at":"2026-07-05T08:31:27.024273+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVQDF24E","created_at":"2026-07-05T08:31:27.024273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.18231","citing_title":"Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO","json":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO.json","graph_json":"https://pith.science/api/pith-number/MVQDF24ESRKU6DOROP4XAURNPO/graph.json","events_json":"https://pith.science/api/pith-number/MVQDF24ESRKU6DOROP4XAURNPO/events.json","paper":"https://pith.science/paper/MVQDF24E"},"agent_actions":{"view_html":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO","download_json":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO.json","view_paper":"https://pith.science/paper/MVQDF24E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09003&json=true","fetch_graph":"https://pith.science/api/pith-number/MVQDF24ESRKU6DOROP4XAURNPO/graph.json","fetch_events":"https://pith.science/api/pith-number/MVQDF24ESRKU6DOROP4XAURNPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO/action/storage_attestation","attest_author":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO/action/author_attestation","sign_citation":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO/action/citation_signature","submit_replication":"https://pith.science/pith/MVQDF24ESRKU6DOROP4XAURNPO/action/replication_record"}},"created_at":"2026-07-05T08:31:27.024273+00:00","updated_at":"2026-07-05T08:31:27.024273+00:00"}