{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LR6XUOXIWD5HFM267VUIBIYEK5","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":"6bd17963db166fc6a0f3b0aeb0d464b2fdccdace7c13253c52ff7f3664d9d80b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T03:36:31Z","title_canon_sha256":"5751beaaa7c77d40cd4c6a872dfe302392daa7ed62923420f8dcd407acd23d6e"},"schema_version":"1.0","source":{"id":"2405.14142","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14142","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14142v2","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14142","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"LR6XUOXIWD5H","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"LR6XUOXIWD5HFM26","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"LR6XUOXI","created_at":"2026-07-05T10:49:44Z"}],"graph_snapshots":[{"event_id":"sha256:58414eea1d2fd2868894aac9a5b7a4df280bc8430b9b2ce62719966cd8f63fdf","target":"graph","created_at":"2026-07-05T10:49:44Z","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/2405.14142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a multimodal dataset where users express preferences through images. These images encompass a broad spectrum of visual expressions ranging from landscapes to artistic depictions. Users request recommendations for books or music that evoke similar feelings to those captured in the images, and recommendations are endorsed by the community through upvotes. This dataset supports two recommendation tasks: title generation and multiple-choice selection. Our experiments with large foundation models reveal their limitations in these tasks. Particularly, vision-language models show no sign","authors_text":"Hyunsik Jeon, Julian McAuley, Se-eun Yoon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T03:36:31Z","title":"Imagery as Inquiry: Exploring A Multimodal Dataset for Conversational Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14142","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:ccc16647047acf085b116ad721c1d021648836b9654f2d4a9462ab3b7db50527","target":"record","created_at":"2026-07-05T10:49:44Z","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":"6bd17963db166fc6a0f3b0aeb0d464b2fdccdace7c13253c52ff7f3664d9d80b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T03:36:31Z","title_canon_sha256":"5751beaaa7c77d40cd4c6a872dfe302392daa7ed62923420f8dcd407acd23d6e"},"schema_version":"1.0","source":{"id":"2405.14142","kind":"arxiv","version":2}},"canonical_sha256":"5c7d7a3ae8b0fa72b35efd6880a304576bd718fa73982fbfcc3645a7b9387c31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7d7a3ae8b0fa72b35efd6880a304576bd718fa73982fbfcc3645a7b9387c31","first_computed_at":"2026-07-05T10:49:44.633130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:44.633130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XmT1qQ5zthgWQjj7YOxqC5xEIxiM4XMMJSMnorbNDcssRn3j9OuqF54sKdjr+SGmjtC7VmKEi1A8P9KUubk2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:44.633575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14142","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc16647047acf085b116ad721c1d021648836b9654f2d4a9462ab3b7db50527","sha256:58414eea1d2fd2868894aac9a5b7a4df280bc8430b9b2ce62719966cd8f63fdf"],"state_sha256":"83fbff3b2b2b364aa4334e68b26553a6bbef4144ff0c01a8043af0810df9a2c8"}