{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VPQLB3PCU2PWJFKODPORXA4JBG","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":"998bca5aaeddbb51829642b851381d23b278f6bfc3abda55991ff84cd46247b2","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T19:01:17Z","title_canon_sha256":"7af5f436baea051c3aec7d83da98904f450cc0aba8b988e5af198290cd33078b"},"schema_version":"1.0","source":{"id":"2503.01980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01980","created_at":"2026-07-05T10:23:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01980v1","created_at":"2026-07-05T10:23:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01980","created_at":"2026-07-05T10:23:33Z"},{"alias_kind":"pith_short_12","alias_value":"VPQLB3PCU2PW","created_at":"2026-07-05T10:23:33Z"},{"alias_kind":"pith_short_16","alias_value":"VPQLB3PCU2PWJFKO","created_at":"2026-07-05T10:23:33Z"},{"alias_kind":"pith_short_8","alias_value":"VPQLB3PC","created_at":"2026-07-05T10:23:33Z"}],"graph_snapshots":[{"event_id":"sha256:6d432688e65f403816cb1076ebfba126748e9dc9f9ab5421fbb978027f0d05bb","target":"graph","created_at":"2026-07-05T10:23:33Z","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/2503.01980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move a step forward and design an approach that allows for multimodal queries, composed of both an image and a text, and can search within collections of multimodal documents, where images and text are interleaved. Our model, ReT, employs multi-level representations extracted from different layers of both visual and textual backbones, both at the query and docum","authors_text":"Davide Caffagni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara, Sara Sarto","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T19:01:17Z","title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01980","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":"sha256:64bd27cbb1545c26aa5c25384fc7ab623b9d868e889f6f28a95c4a86736b642d","target":"record","created_at":"2026-07-05T10:23:33Z","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":"998bca5aaeddbb51829642b851381d23b278f6bfc3abda55991ff84cd46247b2","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T19:01:17Z","title_canon_sha256":"7af5f436baea051c3aec7d83da98904f450cc0aba8b988e5af198290cd33078b"},"schema_version":"1.0","source":{"id":"2503.01980","kind":"arxiv","version":1}},"canonical_sha256":"abe0b0ede2a69f64954e1bdd1b838909aef060090cac3483eaae5e61ec4924dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe0b0ede2a69f64954e1bdd1b838909aef060090cac3483eaae5e61ec4924dd","first_computed_at":"2026-07-05T10:23:33.949203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:33.949203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2NrIOBc8zqNLy82UiX1zFocovfzcSxa9UyiETSW6/XE/RnKytDTTPbZCZSsISQhp1buK1kqlHiQ7lg2v8pY9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:33.949703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64bd27cbb1545c26aa5c25384fc7ab623b9d868e889f6f28a95c4a86736b642d","sha256:6d432688e65f403816cb1076ebfba126748e9dc9f9ab5421fbb978027f0d05bb"],"state_sha256":"009c180664a9d4598f1adae07fad557e00f1850e3956e86b28847447ea838aca"}