{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ACRLGGDINNYOYSTNEJAHIN6UXX","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":"5c35c05ed27f229724e918df0afdbc6c3d5ffcf35998440b69f5adb84e8caf4f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T18:00:29Z","title_canon_sha256":"237176ee61f215e637a0d011bae2d6de22e749b6bf2170049fd5be1f00b49836"},"schema_version":"1.0","source":{"id":"2509.08897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08897","created_at":"2026-07-05T12:08:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08897v1","created_at":"2026-07-05T12:08:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08897","created_at":"2026-07-05T12:08:38Z"},{"alias_kind":"pith_short_12","alias_value":"ACRLGGDINNYO","created_at":"2026-07-05T12:08:38Z"},{"alias_kind":"pith_short_16","alias_value":"ACRLGGDINNYOYSTN","created_at":"2026-07-05T12:08:38Z"},{"alias_kind":"pith_short_8","alias_value":"ACRLGGDI","created_at":"2026-07-05T12:08:38Z"}],"graph_snapshots":[{"event_id":"sha256:dd238cba1651ea7256f7be1f63127435ed6627fd0b7556e7792cb97b5e68d716","target":"graph","created_at":"2026-07-05T12:08:38Z","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/2509.08897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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":"2025-09-10T18:00:29Z","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08897","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":"sha256:430637ebb100568a078234af0fc7fb608ef86bf661682e6fbec3fb15456279e4","target":"record","created_at":"2026-07-05T12:08:38Z","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":"5c35c05ed27f229724e918df0afdbc6c3d5ffcf35998440b69f5adb84e8caf4f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T18:00:29Z","title_canon_sha256":"237176ee61f215e637a0d011bae2d6de22e749b6bf2170049fd5be1f00b49836"},"schema_version":"1.0","source":{"id":"2509.08897","kind":"arxiv","version":1}},"canonical_sha256":"00a2b318686b70ec4a6d22407437d4bdc2ff7d597ea624d72d74b280be720489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00a2b318686b70ec4a6d22407437d4bdc2ff7d597ea624d72d74b280be720489","first_computed_at":"2026-07-05T12:08:38.879407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:38.879407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ox3qJxgtR22JRdOElTp6ZNX5c0FGe4IOc8nIc7o3kFlEd4QMeN70Tksv57ZX5tzyAq2rFPW5GQU/bUqu5o2bBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:38.879945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:430637ebb100568a078234af0fc7fb608ef86bf661682e6fbec3fb15456279e4","sha256:dd238cba1651ea7256f7be1f63127435ed6627fd0b7556e7792cb97b5e68d716"],"state_sha256":"beebeabb9c6ac197e9875b898b0308f309ed98422248789fd4d21fada44a8c11"}