{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DOTXF6VW4FT4UXKTGHRWCDJW5F","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":"bb367773337c38d73734ac4c805884d0cc0c9c5eb38503de6cf2ef2eda4be8fc","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T02:40:49Z","title_canon_sha256":"01adc8454bd37317fd0924bf1d47334a0c70de05240a8bd52168a04d7240d5c7"},"schema_version":"1.0","source":{"id":"2607.22643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22643","created_at":"2026-07-28T00:21:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22643v1","created_at":"2026-07-28T00:21:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22643","created_at":"2026-07-28T00:21:46Z"},{"alias_kind":"pith_short_12","alias_value":"DOTXF6VW4FT4","created_at":"2026-07-28T00:21:46Z"},{"alias_kind":"pith_short_16","alias_value":"DOTXF6VW4FT4UXKT","created_at":"2026-07-28T00:21:46Z"},{"alias_kind":"pith_short_8","alias_value":"DOTXF6VW","created_at":"2026-07-28T00:21:46Z"}],"graph_snapshots":[{"event_id":"sha256:5b0ac35718ccb71eeee35495afa63395e3c75276c18ba859eb3c65698c373927","target":"graph","created_at":"2026-07-28T00:21:46Z","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/2607.22643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal retrieval-augmented generation (mRAG) aims to answer image-text queries with external knowledge, but most existing systems still retrieve directly from raw multimodal input over a flat evidence space. This design often struggles with two key challenges: the retrieval target is under-specified because the question intent must be grounded to the correct visual referent, and the search space is weakly structured, forcing semantically distinct evidence to compete in a single global ranking step. We propose MM-R2, a multimodal agentic retrieval framework that reasons before retrieval by ","authors_text":"Minhao Cheng, Shir Simon, Tianyu Yang, Xiangliang Zhang, Zhenzhen Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T02:40:49Z","title":"Reason Before You Retrieve: Agentic Planning for Multi-modal RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22643","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":"sha256:786adc78fc0e4226b2e5e28467e9bb079346bfa439825e3361ebfc4140b41835","target":"record","created_at":"2026-07-28T00:21:46Z","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":"bb367773337c38d73734ac4c805884d0cc0c9c5eb38503de6cf2ef2eda4be8fc","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T02:40:49Z","title_canon_sha256":"01adc8454bd37317fd0924bf1d47334a0c70de05240a8bd52168a04d7240d5c7"},"schema_version":"1.0","source":{"id":"2607.22643","kind":"arxiv","version":1}},"canonical_sha256":"1ba772fab6e167ca5d5331e3610d36e97b1929b3c9ff877160e118afff4e278c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ba772fab6e167ca5d5331e3610d36e97b1929b3c9ff877160e118afff4e278c","first_computed_at":"2026-07-28T00:21:46.851547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:46.851547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h3zlSw3E5G+6evpbwOSyjmy8X+YnA+H5pyQjJt+lCpqyq9rLFXGYlmNu143Y6jN1tD99Hb2LhPFHH+ZmUMTDAg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:46.852475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:786adc78fc0e4226b2e5e28467e9bb079346bfa439825e3361ebfc4140b41835","sha256:5b0ac35718ccb71eeee35495afa63395e3c75276c18ba859eb3c65698c373927"],"state_sha256":"90a5d116b67be8266c0c3a43e1e1d0817ac404cfb5369c9e9875724fda714814"}