{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R6HX3OCDW6VSK4DRWMV6ESM5TC","short_pith_number":"pith:R6HX3OCD","schema_version":"1.0","canonical_sha256":"8f8f7db843b7ab257071b32be2499d98aafed345cbdb402df4633a6be90dcf4f","source":{"kind":"arxiv","id":"2406.03411","version":2},"attestation_state":"computed","paper":{"title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Yi, Junsung Park, Saehyung Lee, Sangwon Yu, Sungroh Yoon","submitted_at":"2024-06-05T16:09:01Z","abstract_excerpt":"In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task. Our methodology, PlugIR, actively utilizes the general instruction-following capability of LLMs in two ways. First, by reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data, thereby enabling the use of any arbitrary black-box model. Second, we construct the LLM questioner to generate non-redundant questions about the attributes of the target image, based on the information of retrieval c"},"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":"2406.03411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T16:09:01Z","cross_cats_sorted":[],"title_canon_sha256":"281d866c8745f0378e00a75378facef0cebe964e8857b33bc0bbe140a13e3294","abstract_canon_sha256":"a4f08a14bc9abd9a57fb5219fb47d9232d3af46483d5b91e90660a3f3c29fc40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:14.903926Z","signature_b64":"JiRD5PBAsnA66NfSTv8mG3rOM6V1MQthfgfqFxSlKnBnqRYR+Te/4gy0NMect193XmlPZvORCb/6mVTz0p12Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8f7db843b7ab257071b32be2499d98aafed345cbdb402df4633a6be90dcf4f","last_reissued_at":"2026-07-05T08:48:14.903465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:14.903465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Yi, Junsung Park, Saehyung Lee, Sangwon Yu, Sungroh Yoon","submitted_at":"2024-06-05T16:09:01Z","abstract_excerpt":"In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task. Our methodology, PlugIR, actively utilizes the general instruction-following capability of LLMs in two ways. First, by reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data, thereby enabling the use of any arbitrary black-box model. Second, we construct the LLM questioner to generate non-redundant questions about the attributes of the target image, based on the information of retrieval c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03411","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/2406.03411/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":"2406.03411","created_at":"2026-07-05T08:48:14.903523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03411v2","created_at":"2026-07-05T08:48:14.903523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03411","created_at":"2026-07-05T08:48:14.903523+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6HX3OCDW6VS","created_at":"2026-07-05T08:48:14.903523+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6HX3OCDW6VSK4DR","created_at":"2026-07-05T08:48:14.903523+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6HX3OCD","created_at":"2026-07-05T08:48:14.903523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23370","citing_title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC","json":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC.json","graph_json":"https://pith.science/api/pith-number/R6HX3OCDW6VSK4DRWMV6ESM5TC/graph.json","events_json":"https://pith.science/api/pith-number/R6HX3OCDW6VSK4DRWMV6ESM5TC/events.json","paper":"https://pith.science/paper/R6HX3OCD"},"agent_actions":{"view_html":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC","download_json":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC.json","view_paper":"https://pith.science/paper/R6HX3OCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03411&json=true","fetch_graph":"https://pith.science/api/pith-number/R6HX3OCDW6VSK4DRWMV6ESM5TC/graph.json","fetch_events":"https://pith.science/api/pith-number/R6HX3OCDW6VSK4DRWMV6ESM5TC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC/action/storage_attestation","attest_author":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC/action/author_attestation","sign_citation":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC/action/citation_signature","submit_replication":"https://pith.science/pith/R6HX3OCDW6VSK4DRWMV6ESM5TC/action/replication_record"}},"created_at":"2026-07-05T08:48:14.903523+00:00","updated_at":"2026-07-05T08:48:14.903523+00:00"}