{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MPH343APF3LJH5HC2ZASP6OLRH","short_pith_number":"pith:MPH343AP","schema_version":"1.0","canonical_sha256":"63cfbe6c0f2ed693f4e2d64127f9cb89f3925040ea91b01a6ae9b1841cd48a8f","source":{"kind":"arxiv","id":"2406.06048","version":2},"attestation_state":"computed","paper":{"title":"Robust Latent Representation Tuning for Image-text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Sun, Yu Song","submitted_at":"2024-06-10T06:29:00Z","abstract_excerpt":"Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the challenges posed by scenarios where one modality is absent remains a significant hurdle. In response to this issue, we propose a robust latent representation tuning method for large models. Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation. Following "},"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":"2406.06048","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T06:29:00Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"043cb30658509ddf668f7397423198887e5820a1fac31ff5683df609fdcc3264","abstract_canon_sha256":"cc4fb928b60483c04022618ef46635a89ddae0c69a420a266ff88fdc24c7f6d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:52.551007Z","signature_b64":"8uvQ4AXRIUTjIwQVjbcO6NKOydy+8wAJZQXmnEdbejpFVByG+1rjI9aX3Ami91N84Zo9twDZzezdM6a3raAECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63cfbe6c0f2ed693f4e2d64127f9cb89f3925040ea91b01a6ae9b1841cd48a8f","last_reissued_at":"2026-07-05T08:31:52.550496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:52.550496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Latent Representation Tuning for Image-text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Sun, Yu Song","submitted_at":"2024-06-10T06:29:00Z","abstract_excerpt":"Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the challenges posed by scenarios where one modality is absent remains a significant hurdle. In response to this issue, we propose a robust latent representation tuning method for large models. Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation. Following "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06048","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/2406.06048/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":"2406.06048","created_at":"2026-07-05T08:31:52.550556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06048v2","created_at":"2026-07-05T08:31:52.550556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06048","created_at":"2026-07-05T08:31:52.550556+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPH343APF3LJ","created_at":"2026-07-05T08:31:52.550556+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPH343APF3LJH5HC","created_at":"2026-07-05T08:31:52.550556+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPH343AP","created_at":"2026-07-05T08:31:52.550556+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/MPH343APF3LJH5HC2ZASP6OLRH","json":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH.json","graph_json":"https://pith.science/api/pith-number/MPH343APF3LJH5HC2ZASP6OLRH/graph.json","events_json":"https://pith.science/api/pith-number/MPH343APF3LJH5HC2ZASP6OLRH/events.json","paper":"https://pith.science/paper/MPH343AP"},"agent_actions":{"view_html":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH","download_json":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH.json","view_paper":"https://pith.science/paper/MPH343AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06048&json=true","fetch_graph":"https://pith.science/api/pith-number/MPH343APF3LJH5HC2ZASP6OLRH/graph.json","fetch_events":"https://pith.science/api/pith-number/MPH343APF3LJH5HC2ZASP6OLRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH/action/storage_attestation","attest_author":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH/action/author_attestation","sign_citation":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH/action/citation_signature","submit_replication":"https://pith.science/pith/MPH343APF3LJH5HC2ZASP6OLRH/action/replication_record"}},"created_at":"2026-07-05T08:31:52.550556+00:00","updated_at":"2026-07-05T08:31:52.550556+00:00"}