{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UEQWJQPJ6ATBXRSDMU4JZYCC3I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fd74720e1f8284fb1508f56809090d6bcfea885fa460989afc1336de888a747e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:15:44Z","title_canon_sha256":"94a99cf369adce3de38a03b546443d98192ae328f891d34beb34974f5b172d54"},"schema_version":"1.0","source":{"id":"2507.07415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07415","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07415v1","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07415","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"UEQWJQPJ6ATB","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"UEQWJQPJ6ATBXRSD","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"UEQWJQPJ","created_at":"2026-07-05T11:34:57Z"}],"graph_snapshots":[{"event_id":"sha256:8a6d219ca14b80a5565beb97dc351b1583f842c8a7b7bb405db35ebbe1d210bb","target":"graph","created_at":"2026-07-05T11:34:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.07415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Sun, Lanfen Lin, Rui Qin, Xinyao Yu, Yen-Wei Chen, Zeyu Ling, Zhenjia Bai, Ziwei Niu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:15:44Z","title":"EPIC: Efficient Prompt Interaction for Text-Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07415","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c8695f2090d74b22e9f68a568ce363e26b8418d8f3046991ebbc563b683d0a9","target":"record","created_at":"2026-07-05T11:34:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fd74720e1f8284fb1508f56809090d6bcfea885fa460989afc1336de888a747e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:15:44Z","title_canon_sha256":"94a99cf369adce3de38a03b546443d98192ae328f891d34beb34974f5b172d54"},"schema_version":"1.0","source":{"id":"2507.07415","kind":"arxiv","version":1}},"canonical_sha256":"a12164c1e9f0261bc64365389ce042da0dbe8a60342e89b0b07b4a5987601d2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a12164c1e9f0261bc64365389ce042da0dbe8a60342e89b0b07b4a5987601d2a","first_computed_at":"2026-07-05T11:34:57.527766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:57.527766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+HhGfsUhNpLfFkUYQJWDtlgT771Fxrlw924BCnTK7+ceJfnjiNsRbWYrHZQonAz5jD3DLywBEiobM9riKNsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:57.528262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c8695f2090d74b22e9f68a568ce363e26b8418d8f3046991ebbc563b683d0a9","sha256:8a6d219ca14b80a5565beb97dc351b1583f842c8a7b7bb405db35ebbe1d210bb"],"state_sha256":"697a4fec1af44a94f0f5b1f59534c335d4b6e70817f30f02b09ef1e6205751f6"}