{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VPQLB3PCU2PWJFKODPORXA4JBG","short_pith_number":"pith:VPQLB3PC","schema_version":"1.0","canonical_sha256":"abe0b0ede2a69f64954e1bdd1b838909aef060090cac3483eaae5e61ec4924dd","source":{"kind":"arxiv","id":"2503.01980","version":1},"attestation_state":"computed","paper":{"title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Davide Caffagni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara, Sara Sarto","submitted_at":"2025-03-03T19:01:17Z","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"},"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":"2503.01980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T19:01:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"7af5f436baea051c3aec7d83da98904f450cc0aba8b988e5af198290cd33078b","abstract_canon_sha256":"998bca5aaeddbb51829642b851381d23b278f6bfc3abda55991ff84cd46247b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:33.949703Z","signature_b64":"2NrIOBc8zqNLy82UiX1zFocovfzcSxa9UyiETSW6/XE/RnKytDTTPbZCZSsISQhp1buK1kqlHiQ7lg2v8pY9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe0b0ede2a69f64954e1bdd1b838909aef060090cac3483eaae5e61ec4924dd","last_reissued_at":"2026-07-05T10:23:33.949203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:33.949203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Davide Caffagni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara, Sara Sarto","submitted_at":"2025-03-03T19:01:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01980","kind":"arxiv","version":1},"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/2503.01980/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":"2503.01980","created_at":"2026-07-05T10:23:33.949262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01980v1","created_at":"2026-07-05T10:23:33.949262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01980","created_at":"2026-07-05T10:23:33.949262+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPQLB3PCU2PW","created_at":"2026-07-05T10:23:33.949262+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPQLB3PCU2PWJFKO","created_at":"2026-07-05T10:23:33.949262+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPQLB3PC","created_at":"2026-07-05T10:23:33.949262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18831","citing_title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG","json":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG.json","graph_json":"https://pith.science/api/pith-number/VPQLB3PCU2PWJFKODPORXA4JBG/graph.json","events_json":"https://pith.science/api/pith-number/VPQLB3PCU2PWJFKODPORXA4JBG/events.json","paper":"https://pith.science/paper/VPQLB3PC"},"agent_actions":{"view_html":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG","download_json":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG.json","view_paper":"https://pith.science/paper/VPQLB3PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01980&json=true","fetch_graph":"https://pith.science/api/pith-number/VPQLB3PCU2PWJFKODPORXA4JBG/graph.json","fetch_events":"https://pith.science/api/pith-number/VPQLB3PCU2PWJFKODPORXA4JBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG/action/storage_attestation","attest_author":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG/action/author_attestation","sign_citation":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG/action/citation_signature","submit_replication":"https://pith.science/pith/VPQLB3PCU2PWJFKODPORXA4JBG/action/replication_record"}},"created_at":"2026-07-05T10:23:33.949262+00:00","updated_at":"2026-07-05T10:23:33.949262+00:00"}