{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ACRLGGDINNYOYSTNEJAHIN6UXX","short_pith_number":"pith:ACRLGGDI","schema_version":"1.0","canonical_sha256":"00a2b318686b70ec4a6d22407437d4bdc2ff7d597ea624d72d74b280be720489","source":{"kind":"arxiv","id":"2509.08897","version":1},"attestation_state":"computed","paper":{"title":"Recurrence Meets Transformers for Universal Multimodal 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":"2025-09-10T18:00:29Z","abstract_excerpt":"With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language models and are limited to single-modality queries or documents. In this paper, we propose ReT-2, a unified retrieval model that supports multimodal queries, composed of both images and text, and searches across multimodal document collections where text and images coexist. ReT-2 leverages multi-layer representations and a recurrent Transformer architecture with L"},"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":"2509.08897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T18:00:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"237176ee61f215e637a0d011bae2d6de22e749b6bf2170049fd5be1f00b49836","abstract_canon_sha256":"5c35c05ed27f229724e918df0afdbc6c3d5ffcf35998440b69f5adb84e8caf4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:38.879945Z","signature_b64":"Ox3qJxgtR22JRdOElTp6ZNX5c0FGe4IOc8nIc7o3kFlEd4QMeN70Tksv57ZX5tzyAq2rFPW5GQU/bUqu5o2bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a2b318686b70ec4a6d22407437d4bdc2ff7d597ea624d72d74b280be720489","last_reissued_at":"2026-07-05T12:08:38.879407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:38.879407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrence Meets Transformers for Universal Multimodal 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":"2025-09-10T18:00:29Z","abstract_excerpt":"With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language models and are limited to single-modality queries or documents. In this paper, we propose ReT-2, a unified retrieval model that supports multimodal queries, composed of both images and text, and searches across multimodal document collections where text and images coexist. ReT-2 leverages multi-layer representations and a recurrent Transformer architecture with L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08897","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/2509.08897/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":"2509.08897","created_at":"2026-07-05T12:08:38.879482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08897v1","created_at":"2026-07-05T12:08:38.879482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08897","created_at":"2026-07-05T12:08:38.879482+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACRLGGDINNYO","created_at":"2026-07-05T12:08:38.879482+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACRLGGDINNYOYSTN","created_at":"2026-07-05T12:08:38.879482+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACRLGGDI","created_at":"2026-07-05T12:08:38.879482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21806","citing_title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX","json":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX.json","graph_json":"https://pith.science/api/pith-number/ACRLGGDINNYOYSTNEJAHIN6UXX/graph.json","events_json":"https://pith.science/api/pith-number/ACRLGGDINNYOYSTNEJAHIN6UXX/events.json","paper":"https://pith.science/paper/ACRLGGDI"},"agent_actions":{"view_html":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX","download_json":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX.json","view_paper":"https://pith.science/paper/ACRLGGDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08897&json=true","fetch_graph":"https://pith.science/api/pith-number/ACRLGGDINNYOYSTNEJAHIN6UXX/graph.json","fetch_events":"https://pith.science/api/pith-number/ACRLGGDINNYOYSTNEJAHIN6UXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX/action/storage_attestation","attest_author":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX/action/author_attestation","sign_citation":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX/action/citation_signature","submit_replication":"https://pith.science/pith/ACRLGGDINNYOYSTNEJAHIN6UXX/action/replication_record"}},"created_at":"2026-07-05T12:08:38.879482+00:00","updated_at":"2026-07-05T12:08:38.879482+00:00"}