{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7XCZC3HFJGD53BM5BSXADBTFHN","short_pith_number":"pith:7XCZC3HF","canonical_record":{"source":{"id":"2505.07879","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-10T14:24:41Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"813ddd6dd502d5cdea26d3643b10572339b4016b491b6d8ede7e0e8dde9c0d21","abstract_canon_sha256":"57ce058e0c33bad79b6a063c89490cd688df8c88c07776af3e8858d1ae2f0dd6"},"schema_version":"1.0"},"canonical_sha256":"fdc5916ce54987dd859d0cae0186653b6a3fd9540d40960523f0f136481a78ab","source":{"kind":"arxiv","id":"2505.07879","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07879","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07879v3","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07879","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"7XCZC3HFJGD5","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"7XCZC3HFJGD53BM5","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"7XCZC3HF","created_at":"2026-07-05T12:10:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7XCZC3HFJGD53BM5BSXADBTFHN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07879","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-10T14:24:41Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"813ddd6dd502d5cdea26d3643b10572339b4016b491b6d8ede7e0e8dde9c0d21","abstract_canon_sha256":"57ce058e0c33bad79b6a063c89490cd688df8c88c07776af3e8858d1ae2f0dd6"},"schema_version":"1.0"},"canonical_sha256":"fdc5916ce54987dd859d0cae0186653b6a3fd9540d40960523f0f136481a78ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:57.788704Z","signature_b64":"sd8a10NqZUcU2AtO1xnisc7vCzS6o8qlKLtSj/cBpcFI2j1w5BxfitS1Zc3+QZUUA2dqhqU4VWiwtLjrCYucDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdc5916ce54987dd859d0cae0186653b6a3fd9540d40960523f0f136481a78ab","last_reissued_at":"2026-07-05T12:10:57.788177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:57.788177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07879","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"riqA+deDIuql7zIAYy0wQ9HTNYszQ/NLOfojHeYCJky9fJJzKq2Btz1X4Og9kzPPtxCOJQb5SXOusoG0eqInBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:56:31.146739Z"},"content_sha256":"b444143baafd0d71212f64e2301ec749b01a57bc5f65b0f8dde6304c34975929","schema_version":"1.0","event_id":"sha256:b444143baafd0d71212f64e2301ec749b01a57bc5f65b0f8dde6304c34975929"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7XCZC3HFJGD53BM5BSXADBTFHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.IR","authors_text":"Jiang Bian, Jingjing Fu, Jinyu Wang, Lei Song, Rui Wang, Wei Yang","submitted_at":"2025-05-10T14:24:41Z","abstract_excerpt":"Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge beyond the visual content presented in images. The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases. Existing methods have not fully tapped into the potential interplay between these elements. We propose a multimodal RAG system featuring a coarse-to-fine, multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07879","kind":"arxiv","version":3},"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/2505.07879/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":"2026-07-05T12:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ww4Bj2u/nuvjP97K74wRI9dTZwouC8KAnK4Eot8qDr41tA3dQD/xf0oH8LaKjwnlCLXyLY/LC93n5HdJWuJlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:56:31.147249Z"},"content_sha256":"c55542b25aa5cde8ab31d064c82eb580a6e849365d479b63d073cea6a07eb2f7","schema_version":"1.0","event_id":"sha256:c55542b25aa5cde8ab31d064c82eb580a6e849365d479b63d073cea6a07eb2f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XCZC3HFJGD53BM5BSXADBTFHN/bundle.json","state_url":"https://pith.science/pith/7XCZC3HFJGD53BM5BSXADBTFHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XCZC3HFJGD53BM5BSXADBTFHN/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":"2026-08-08T12:56:31Z","links":{"resolver":"https://pith.science/pith/7XCZC3HFJGD53BM5BSXADBTFHN","bundle":"https://pith.science/pith/7XCZC3HFJGD53BM5BSXADBTFHN/bundle.json","state":"https://pith.science/pith/7XCZC3HFJGD53BM5BSXADBTFHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XCZC3HFJGD53BM5BSXADBTFHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7XCZC3HFJGD53BM5BSXADBTFHN","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":"57ce058e0c33bad79b6a063c89490cd688df8c88c07776af3e8858d1ae2f0dd6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-10T14:24:41Z","title_canon_sha256":"813ddd6dd502d5cdea26d3643b10572339b4016b491b6d8ede7e0e8dde9c0d21"},"schema_version":"1.0","source":{"id":"2505.07879","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07879","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07879v3","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07879","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"7XCZC3HFJGD5","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"7XCZC3HFJGD53BM5","created_at":"2026-07-05T12:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"7XCZC3HF","created_at":"2026-07-05T12:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:c55542b25aa5cde8ab31d064c82eb580a6e849365d479b63d073cea6a07eb2f7","target":"graph","created_at":"2026-07-05T12:10:57Z","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/2505.07879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge beyond the visual content presented in images. The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases. Existing methods have not fully tapped into the potential interplay between these elements. We propose a multimodal RAG system featuring a coarse-to-fine, multi","authors_text":"Jiang Bian, Jingjing Fu, Jinyu Wang, Lei Song, Rui Wang, Wei Yang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-10T14:24:41Z","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07879","kind":"arxiv","version":3},"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:b444143baafd0d71212f64e2301ec749b01a57bc5f65b0f8dde6304c34975929","target":"record","created_at":"2026-07-05T12:10:57Z","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":"57ce058e0c33bad79b6a063c89490cd688df8c88c07776af3e8858d1ae2f0dd6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-10T14:24:41Z","title_canon_sha256":"813ddd6dd502d5cdea26d3643b10572339b4016b491b6d8ede7e0e8dde9c0d21"},"schema_version":"1.0","source":{"id":"2505.07879","kind":"arxiv","version":3}},"canonical_sha256":"fdc5916ce54987dd859d0cae0186653b6a3fd9540d40960523f0f136481a78ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdc5916ce54987dd859d0cae0186653b6a3fd9540d40960523f0f136481a78ab","first_computed_at":"2026-07-05T12:10:57.788177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:10:57.788177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sd8a10NqZUcU2AtO1xnisc7vCzS6o8qlKLtSj/cBpcFI2j1w5BxfitS1Zc3+QZUUA2dqhqU4VWiwtLjrCYucDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:10:57.788704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07879","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b444143baafd0d71212f64e2301ec749b01a57bc5f65b0f8dde6304c34975929","sha256:c55542b25aa5cde8ab31d064c82eb580a6e849365d479b63d073cea6a07eb2f7"],"state_sha256":"6c7b6c34615dbf3d12248b691f492f9361e57ceb589e9334d095870ea3c7dc68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDDXsUjNzSXCnhDmoPIj73wHcrL2ABBDSyXtG1hQxaOKCCRBLU6jnMWKbyz0JQj92CvXN3lHFa5V+/Z6071KAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:56:31.153414Z","bundle_sha256":"c7c596f741a2fceea1dfb02d2f426111d66c2bb8217383da8d7d3d8d0814f5ea"}}