{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UEQWJQPJ6ATBXRSDMU4JZYCC3I","short_pith_number":"pith:UEQWJQPJ","schema_version":"1.0","canonical_sha256":"a12164c1e9f0261bc64365389ce042da0dbe8a60342e89b0b07b4a5987601d2a","source":{"kind":"arxiv","id":"2507.07415","version":1},"attestation_state":"computed","paper":{"title":"EPIC: Efficient Prompt Interaction for Text-Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Sun, Lanfen Lin, Rui Qin, Xinyao Yu, Yen-Wei Chen, Zeyu Ling, Zhenjia Bai, Ziwei Niu","submitted_at":"2025-07-10T04:15:44Z","abstract_excerpt":"In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of LMMs, however, results in a significant computational cost for fine-tuning these models for downstream tasks. Hence, prompt-based interaction strategy is studied to align modalities more efficiently. In this context, we propose a novel efficient prompt-based multimodal interaction strategy, namely Efficient Prompt Interaction for text-image Classification (EP"},"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":"2507.07415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:15:44Z","cross_cats_sorted":[],"title_canon_sha256":"94a99cf369adce3de38a03b546443d98192ae328f891d34beb34974f5b172d54","abstract_canon_sha256":"fd74720e1f8284fb1508f56809090d6bcfea885fa460989afc1336de888a747e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:57.528262Z","signature_b64":"C+HhGfsUhNpLfFkUYQJWDtlgT771Fxrlw924BCnTK7+ceJfnjiNsRbWYrHZQonAz5jD3DLywBEiobM9riKNsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a12164c1e9f0261bc64365389ce042da0dbe8a60342e89b0b07b4a5987601d2a","last_reissued_at":"2026-07-05T11:34:57.527766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:57.527766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EPIC: Efficient Prompt Interaction for Text-Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Sun, Lanfen Lin, Rui Qin, Xinyao Yu, Yen-Wei Chen, Zeyu Ling, Zhenjia Bai, Ziwei Niu","submitted_at":"2025-07-10T04:15:44Z","abstract_excerpt":"In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of LMMs, however, results in a significant computational cost for fine-tuning these models for downstream tasks. Hence, prompt-based interaction strategy is studied to align modalities more efficiently. In this context, we propose a novel efficient prompt-based multimodal interaction strategy, namely Efficient Prompt Interaction for text-image Classification (EP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07415","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/2507.07415/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":"2507.07415","created_at":"2026-07-05T11:34:57.527824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07415v1","created_at":"2026-07-05T11:34:57.527824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07415","created_at":"2026-07-05T11:34:57.527824+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEQWJQPJ6ATB","created_at":"2026-07-05T11:34:57.527824+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEQWJQPJ6ATBXRSD","created_at":"2026-07-05T11:34:57.527824+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEQWJQPJ","created_at":"2026-07-05T11:34:57.527824+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/UEQWJQPJ6ATBXRSDMU4JZYCC3I","json":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I.json","graph_json":"https://pith.science/api/pith-number/UEQWJQPJ6ATBXRSDMU4JZYCC3I/graph.json","events_json":"https://pith.science/api/pith-number/UEQWJQPJ6ATBXRSDMU4JZYCC3I/events.json","paper":"https://pith.science/paper/UEQWJQPJ"},"agent_actions":{"view_html":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I","download_json":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I.json","view_paper":"https://pith.science/paper/UEQWJQPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07415&json=true","fetch_graph":"https://pith.science/api/pith-number/UEQWJQPJ6ATBXRSDMU4JZYCC3I/graph.json","fetch_events":"https://pith.science/api/pith-number/UEQWJQPJ6ATBXRSDMU4JZYCC3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I/action/storage_attestation","attest_author":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I/action/author_attestation","sign_citation":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I/action/citation_signature","submit_replication":"https://pith.science/pith/UEQWJQPJ6ATBXRSDMU4JZYCC3I/action/replication_record"}},"created_at":"2026-07-05T11:34:57.527824+00:00","updated_at":"2026-07-05T11:34:57.527824+00:00"}