{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R6HX3OCDW6VSK4DRWMV6ESM5TC","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":"a4f08a14bc9abd9a57fb5219fb47d9232d3af46483d5b91e90660a3f3c29fc40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T16:09:01Z","title_canon_sha256":"281d866c8745f0378e00a75378facef0cebe964e8857b33bc0bbe140a13e3294"},"schema_version":"1.0","source":{"id":"2406.03411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03411","created_at":"2026-07-05T08:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03411v2","created_at":"2026-07-05T08:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03411","created_at":"2026-07-05T08:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"R6HX3OCDW6VS","created_at":"2026-07-05T08:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"R6HX3OCDW6VSK4DR","created_at":"2026-07-05T08:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"R6HX3OCD","created_at":"2026-07-05T08:48:14Z"}],"graph_snapshots":[{"event_id":"sha256:0f390f216806d171b325ee6c0306c508307498cd2a0adb885eb402d80056c362","target":"graph","created_at":"2026-07-05T08:48:14Z","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/2406.03411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jihun Yi, Junsung Park, Saehyung Lee, Sangwon Yu, Sungroh Yoon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T16:09:01Z","title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03411","kind":"arxiv","version":2},"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":"sha256:7babaf4ab001755da6d43b6171bb97da3dff48939526a407256a08427607b0b2","target":"record","created_at":"2026-07-05T08:48:14Z","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":"a4f08a14bc9abd9a57fb5219fb47d9232d3af46483d5b91e90660a3f3c29fc40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T16:09:01Z","title_canon_sha256":"281d866c8745f0378e00a75378facef0cebe964e8857b33bc0bbe140a13e3294"},"schema_version":"1.0","source":{"id":"2406.03411","kind":"arxiv","version":2}},"canonical_sha256":"8f8f7db843b7ab257071b32be2499d98aafed345cbdb402df4633a6be90dcf4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8f7db843b7ab257071b32be2499d98aafed345cbdb402df4633a6be90dcf4f","first_computed_at":"2026-07-05T08:48:14.903465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:14.903465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JiRD5PBAsnA66NfSTv8mG3rOM6V1MQthfgfqFxSlKnBnqRYR+Te/4gy0NMect193XmlPZvORCb/6mVTz0p12Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:14.903926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7babaf4ab001755da6d43b6171bb97da3dff48939526a407256a08427607b0b2","sha256:0f390f216806d171b325ee6c0306c508307498cd2a0adb885eb402d80056c362"],"state_sha256":"e92e49a63bbaa8c2074556e26e20221d515d530bfadd32d65fa93a317f80c2f3"}