{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XIUEWZ2HJC423OFGYMPWNNOFFW","short_pith_number":"pith:XIUEWZ2H","schema_version":"1.0","canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","source":{"kind":"arxiv","id":"2401.01076","version":2},"attestation_state":"computed","paper":{"title":"DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Zhichao Yin","submitted_at":"2024-01-02T07:40:12Z","abstract_excerpt":"Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks. However, the existing pre-trained models primarily focus on effectively capturing the alignment between vision and language modalities, often ignoring the intricate nature of dialog context. In this paper, we propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval. Specifically, our approach introduces a multi-modal cont"},"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":"2401.01076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","cross_cats_sorted":[],"title_canon_sha256":"db8a7544769840255ae3089c75bdf79fdd1e254d7e984c911fdae23461e856fc","abstract_canon_sha256":"871e750ae669ea2f51f2f20444e8be02ec6e3a2ab06e7cc0c0d97e7722e3a29a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:41.386334Z","signature_b64":"psZ3E8MCdPeP/u7wo92EBDtqSP4zWRgiA6GYJucGByNerahv73xoufuspfZ29Pcblx3FdJswYjfnTVfzsI2KAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","last_reissued_at":"2026-07-05T07:29:41.385926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:41.385926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Zhichao Yin","submitted_at":"2024-01-02T07:40:12Z","abstract_excerpt":"Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks. However, the existing pre-trained models primarily focus on effectively capturing the alignment between vision and language modalities, often ignoring the intricate nature of dialog context. In this paper, we propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval. Specifically, our approach introduces a multi-modal cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01076","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/2401.01076/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":"2401.01076","created_at":"2026-07-05T07:29:41.385977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01076v2","created_at":"2026-07-05T07:29:41.385977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01076","created_at":"2026-07-05T07:29:41.385977+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIUEWZ2HJC42","created_at":"2026-07-05T07:29:41.385977+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIUEWZ2HJC423OFG","created_at":"2026-07-05T07:29:41.385977+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIUEWZ2H","created_at":"2026-07-05T07:29:41.385977+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/XIUEWZ2HJC423OFGYMPWNNOFFW","json":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW.json","graph_json":"https://pith.science/api/pith-number/XIUEWZ2HJC423OFGYMPWNNOFFW/graph.json","events_json":"https://pith.science/api/pith-number/XIUEWZ2HJC423OFGYMPWNNOFFW/events.json","paper":"https://pith.science/paper/XIUEWZ2H"},"agent_actions":{"view_html":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW","download_json":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW.json","view_paper":"https://pith.science/paper/XIUEWZ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01076&json=true","fetch_graph":"https://pith.science/api/pith-number/XIUEWZ2HJC423OFGYMPWNNOFFW/graph.json","fetch_events":"https://pith.science/api/pith-number/XIUEWZ2HJC423OFGYMPWNNOFFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/action/storage_attestation","attest_author":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/action/author_attestation","sign_citation":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/action/citation_signature","submit_replication":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/action/replication_record"}},"created_at":"2026-07-05T07:29:41.385977+00:00","updated_at":"2026-07-05T07:29:41.385977+00:00"}