{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJEKAUR6EEFTACELIYWUAC6Z6L","short_pith_number":"pith:JJEKAUR6","schema_version":"1.0","canonical_sha256":"4a48a0523e210b30088b462d400bd9f2c711b351c573910f23b982c2025c3bd8","source":{"kind":"arxiv","id":"2501.10834","version":1},"attestation_state":"computed","paper":{"title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mirco Bonomo, Simone Bianco","submitted_at":"2025-01-18T17:43:05Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring extensive fine-tuning for updates. Recent researches have explored the use of In-Context Learning (ICL) to overcome these challenges by providing a set of demonstrating examples as context to augment MLLMs performance in several tasks, showing that many-shot ICL leads to substantial improvements compared to few-shot ICL. However, the reliance on numerous demonstrat"},"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":"2501.10834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T17:43:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9cc44d9886b00267693f812dea2d33ea9143e8e5717fa62a61ec0c0a203702ff","abstract_canon_sha256":"e75a64d1b877d939b40707fb52f035b20b0eb141517c3e0ed5e3c9276443d3c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:33.896422Z","signature_b64":"smyF/bAOIY5bQdr+eLiQJl91IDLJhCfiBLCxa3zNIjWa3ncvqChCoNnUxkSky7fQ3SX+hfK7EwOY2B1IgYtTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a48a0523e210b30088b462d400bd9f2c711b351c573910f23b982c2025c3bd8","last_reissued_at":"2026-07-05T10:02:33.895980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:33.895980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mirco Bonomo, Simone Bianco","submitted_at":"2025-01-18T17:43:05Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring extensive fine-tuning for updates. Recent researches have explored the use of In-Context Learning (ICL) to overcome these challenges by providing a set of demonstrating examples as context to augment MLLMs performance in several tasks, showing that many-shot ICL leads to substantial improvements compared to few-shot ICL. However, the reliance on numerous demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10834","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/2501.10834/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":"2501.10834","created_at":"2026-07-05T10:02:33.896041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10834v1","created_at":"2026-07-05T10:02:33.896041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10834","created_at":"2026-07-05T10:02:33.896041+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJEKAUR6EEFT","created_at":"2026-07-05T10:02:33.896041+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJEKAUR6EEFTACEL","created_at":"2026-07-05T10:02:33.896041+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJEKAUR6","created_at":"2026-07-05T10:02:33.896041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03833","citing_title":"SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L","json":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L.json","graph_json":"https://pith.science/api/pith-number/JJEKAUR6EEFTACELIYWUAC6Z6L/graph.json","events_json":"https://pith.science/api/pith-number/JJEKAUR6EEFTACELIYWUAC6Z6L/events.json","paper":"https://pith.science/paper/JJEKAUR6"},"agent_actions":{"view_html":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L","download_json":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L.json","view_paper":"https://pith.science/paper/JJEKAUR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10834&json=true","fetch_graph":"https://pith.science/api/pith-number/JJEKAUR6EEFTACELIYWUAC6Z6L/graph.json","fetch_events":"https://pith.science/api/pith-number/JJEKAUR6EEFTACELIYWUAC6Z6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L/action/storage_attestation","attest_author":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L/action/author_attestation","sign_citation":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L/action/citation_signature","submit_replication":"https://pith.science/pith/JJEKAUR6EEFTACELIYWUAC6Z6L/action/replication_record"}},"created_at":"2026-07-05T10:02:33.896041+00:00","updated_at":"2026-07-05T10:02:33.896041+00:00"}