{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6G4ZP6P5SWH7XNTQCCP2HTCLSZ","short_pith_number":"pith:6G4ZP6P5","canonical_record":{"source":{"id":"2404.15406","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T18:00:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"e69584e006317429b290a6931a703b79a07b5a6042eec093b8afbe3ee7ef80a1","abstract_canon_sha256":"cc719402fbdc295ab6496d17967f4f0038ec73884d77019d26e9d88af0964fd1"},"schema_version":"1.0"},"canonical_sha256":"f1b997f9fd958ffbb670109fa3cc4b965734c57b574a29fba57a37547821790c","source":{"kind":"arxiv","id":"2404.15406","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15406","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15406v2","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15406","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"6G4ZP6P5SWH7","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"6G4ZP6P5SWH7XNTQ","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"6G4ZP6P5","created_at":"2026-07-05T08:21:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6G4ZP6P5SWH7XNTQCCP2HTCLSZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15406","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T18:00:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"e69584e006317429b290a6931a703b79a07b5a6042eec093b8afbe3ee7ef80a1","abstract_canon_sha256":"cc719402fbdc295ab6496d17967f4f0038ec73884d77019d26e9d88af0964fd1"},"schema_version":"1.0"},"canonical_sha256":"f1b997f9fd958ffbb670109fa3cc4b965734c57b574a29fba57a37547821790c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:52.909934Z","signature_b64":"QljlyFY1K6gvAWfyk56THIGeycssQh1QKp013ezEOqiNHrahVLsHUXFTQtzElL8l3dLqLrXje8V5Z9JXmQZoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1b997f9fd958ffbb670109fa3cc4b965734c57b574a29fba57a37547821790c","last_reissued_at":"2026-07-05T08:21:52.909162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:52.909162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15406","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BKDnnULIXE8cAwIZjkZ3bpT/UdyFs/DIXkJZsUX/8C1LvXcdYH9FrLdpOQGxT3nBlFsLzhIFbCEFmy75gmAaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:33:59.161827Z"},"content_sha256":"f1b40f95d8d9e63b0f627c84aa2cb77f1ae22bdc64c4f92fe94d2cd576055efa","schema_version":"1.0","event_id":"sha256:f1b40f95d8d9e63b0f627c84aa2cb77f1ae22bdc64c4f92fe94d2cd576055efa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6G4ZP6P5SWH7XNTQCCP2HTCLSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs","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, Federico Cocchi, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, Rita Cucchiara, Sara Sarto","submitted_at":"2024-04-23T18:00:09Z","abstract_excerpt":"Multimodal LLMs are the natural evolution of LLMs, and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters, in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach, termed Wiki-LLaVA, aims at integrating an external knowledge source of multimodal documents, which is accessed through a hierarchical retrieval pipeline. Relevant passages, using this approach, are retrieved from the external know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15406","kind":"arxiv","version":2},"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/2404.15406/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drGDpxSmhQuMs7xUdFuhCWPU7kawxKVD+paPHU9NEpq/sJT5C4/jnM/hIsc9y7LsqTIGKs7C5jRy0uCJyRM4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:33:59.162441Z"},"content_sha256":"cc1182828b7906fb56d0c9c60a2b8d1235df79d13598272aad6032247b13ce4f","schema_version":"1.0","event_id":"sha256:cc1182828b7906fb56d0c9c60a2b8d1235df79d13598272aad6032247b13ce4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/bundle.json","state_url":"https://pith.science/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T05:33:59Z","links":{"resolver":"https://pith.science/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ","bundle":"https://pith.science/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/bundle.json","state":"https://pith.science/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6G4ZP6P5SWH7XNTQCCP2HTCLSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6G4ZP6P5SWH7XNTQCCP2HTCLSZ","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":"cc719402fbdc295ab6496d17967f4f0038ec73884d77019d26e9d88af0964fd1","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T18:00:09Z","title_canon_sha256":"e69584e006317429b290a6931a703b79a07b5a6042eec093b8afbe3ee7ef80a1"},"schema_version":"1.0","source":{"id":"2404.15406","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15406","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15406v2","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15406","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"6G4ZP6P5SWH7","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"6G4ZP6P5SWH7XNTQ","created_at":"2026-07-05T08:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"6G4ZP6P5","created_at":"2026-07-05T08:21:52Z"}],"graph_snapshots":[{"event_id":"sha256:cc1182828b7906fb56d0c9c60a2b8d1235df79d13598272aad6032247b13ce4f","target":"graph","created_at":"2026-07-05T08:21:52Z","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/2404.15406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal LLMs are the natural evolution of LLMs, and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters, in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach, termed Wiki-LLaVA, aims at integrating an external knowledge source of multimodal documents, which is accessed through a hierarchical retrieval pipeline. Relevant passages, using this approach, are retrieved from the external know","authors_text":"Davide Caffagni, Federico Cocchi, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, 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":"2024-04-23T18:00:09Z","title":"Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15406","kind":"arxiv","version":2},"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:f1b40f95d8d9e63b0f627c84aa2cb77f1ae22bdc64c4f92fe94d2cd576055efa","target":"record","created_at":"2026-07-05T08:21:52Z","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":"cc719402fbdc295ab6496d17967f4f0038ec73884d77019d26e9d88af0964fd1","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T18:00:09Z","title_canon_sha256":"e69584e006317429b290a6931a703b79a07b5a6042eec093b8afbe3ee7ef80a1"},"schema_version":"1.0","source":{"id":"2404.15406","kind":"arxiv","version":2}},"canonical_sha256":"f1b997f9fd958ffbb670109fa3cc4b965734c57b574a29fba57a37547821790c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1b997f9fd958ffbb670109fa3cc4b965734c57b574a29fba57a37547821790c","first_computed_at":"2026-07-05T08:21:52.909162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:52.909162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QljlyFY1K6gvAWfyk56THIGeycssQh1QKp013ezEOqiNHrahVLsHUXFTQtzElL8l3dLqLrXje8V5Z9JXmQZoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:52.909934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15406","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1b40f95d8d9e63b0f627c84aa2cb77f1ae22bdc64c4f92fe94d2cd576055efa","sha256:cc1182828b7906fb56d0c9c60a2b8d1235df79d13598272aad6032247b13ce4f"],"state_sha256":"ed463708d156ae991d58b6e2eead77641f3980c405100d375f2b4c429be446c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0QyTYTGvdwOveK66TifXg6IyRCSmTfbAOxadvcDnyCnP8MnHDA5gf7kAqPNlBsHAUd0WWExfKRJO0VEF4L2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:33:59.166624Z","bundle_sha256":"97509917daee51a30f1138a4ca3bc638a162909c65246a6010b7b0d91e01a934"}}