{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KJEBFHU7HFF5FQGVWKOGCVDSFN","short_pith_number":"pith:KJEBFHU7","schema_version":"1.0","canonical_sha256":"5248129e9f394bd2c0d5b29c6154722b6386fa813676febe6f9e50029bacc682","source":{"kind":"arxiv","id":"2605.27959","version":1},"attestation_state":"computed","paper":{"title":"ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guannan Lv, Hongjian Dou, Ren Nie","submitted_at":"2026-05-27T04:52:42Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or RoI-specific features into the reasoning context. However, such designs can weaken holistic scene understanding and inter-object relations, while incurring decoding costs that scale with the number and size of RoIs. Alternatively, adaptive visual feature selection often requires fine-grained supervision or complex heuristics. To address these limitations, we"},"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":"2605.27959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T04:52:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50d7ccf689173e002ac008df3ee542daf5211534d101229640657bd63b314657","abstract_canon_sha256":"9f3d29ba1c5a17db22e875f158dca838cf7ce659391dfd1a1d75899e34ada1a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:54.189537Z","signature_b64":"gcouSwwmEBBlgX3XhFOncXDeNoE8VAZikP9R1lu3t/rS6raToIRV0/QQ6yJFlDE/hvLlPL2xvHa+7eRjTf75Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5248129e9f394bd2c0d5b29c6154722b6386fa813676febe6f9e50029bacc682","last_reissued_at":"2026-05-28T01:04:54.189132Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:54.189132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guannan Lv, Hongjian Dou, Ren Nie","submitted_at":"2026-05-27T04:52:42Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or RoI-specific features into the reasoning context. However, such designs can weaken holistic scene understanding and inter-object relations, while incurring decoding costs that scale with the number and size of RoIs. Alternatively, adaptive visual feature selection often requires fine-grained supervision or complex heuristics. To address these limitations, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27959","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/2605.27959/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":"2605.27959","created_at":"2026-05-28T01:04:54.189187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27959v1","created_at":"2026-05-28T01:04:54.189187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27959","created_at":"2026-05-28T01:04:54.189187+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJEBFHU7HFF5","created_at":"2026-05-28T01:04:54.189187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJEBFHU7HFF5FQGV","created_at":"2026-05-28T01:04:54.189187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJEBFHU7","created_at":"2026-05-28T01:04:54.189187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN","json":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN.json","graph_json":"https://pith.science/api/pith-number/KJEBFHU7HFF5FQGVWKOGCVDSFN/graph.json","events_json":"https://pith.science/api/pith-number/KJEBFHU7HFF5FQGVWKOGCVDSFN/events.json","paper":"https://pith.science/paper/KJEBFHU7"},"agent_actions":{"view_html":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN","download_json":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN.json","view_paper":"https://pith.science/paper/KJEBFHU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27959&json=true","fetch_graph":"https://pith.science/api/pith-number/KJEBFHU7HFF5FQGVWKOGCVDSFN/graph.json","fetch_events":"https://pith.science/api/pith-number/KJEBFHU7HFF5FQGVWKOGCVDSFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN/action/storage_attestation","attest_author":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN/action/author_attestation","sign_citation":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN/action/citation_signature","submit_replication":"https://pith.science/pith/KJEBFHU7HFF5FQGVWKOGCVDSFN/action/replication_record"}},"created_at":"2026-05-28T01:04:54.189187+00:00","updated_at":"2026-05-28T01:04:54.189187+00:00"}