{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:75DM6RXX6MLSIVXOLI2V2OFALL","short_pith_number":"pith:75DM6RXX","schema_version":"1.0","canonical_sha256":"ff46cf46f7f3172456ee5a355d38a05ad7b23af90d308faa9a37b28c020ca09f","source":{"kind":"arxiv","id":"2606.23881","version":1},"attestation_state":"computed","paper":{"title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.CL","authors_text":"Qian Ma, Qiong Wu, Yao Ma, Zhengyi Zhou","submitted_at":"2026-06-22T19:27:00Z","abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images. While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both fine-grained entity and evidence levels. Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization. In this work, we revisit exis"},"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":"2606.23881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T19:27:00Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"f82f908537b26e99d35d538af8b8d48ec3943610858111c4a01925aa6deb39ae","abstract_canon_sha256":"d4e79dc103bde6b1cde324c84008fd4d73a3c7f821b9db096cf9aee14fbe633f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:29.236755Z","signature_b64":"mz3hX9Rm5XZ4Ub0clFtGLC4eLr7znvvRzCpM7MMH6+lUAHZj4VI1y/NK1+e0JGrEl3smACqGYxNPrTXgKFxVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff46cf46f7f3172456ee5a355d38a05ad7b23af90d308faa9a37b28c020ca09f","last_reissued_at":"2026-06-24T00:14:29.236361Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:29.236361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.CL","authors_text":"Qian Ma, Qiong Wu, Yao Ma, Zhengyi Zhou","submitted_at":"2026-06-22T19:27:00Z","abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images. While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both fine-grained entity and evidence levels. Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization. In this work, we revisit exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23881","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/2606.23881/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":"2606.23881","created_at":"2026-06-24T00:14:29.236424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23881v1","created_at":"2026-06-24T00:14:29.236424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23881","created_at":"2026-06-24T00:14:29.236424+00:00"},{"alias_kind":"pith_short_12","alias_value":"75DM6RXX6MLS","created_at":"2026-06-24T00:14:29.236424+00:00"},{"alias_kind":"pith_short_16","alias_value":"75DM6RXX6MLSIVXO","created_at":"2026-06-24T00:14:29.236424+00:00"},{"alias_kind":"pith_short_8","alias_value":"75DM6RXX","created_at":"2026-06-24T00:14:29.236424+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/75DM6RXX6MLSIVXOLI2V2OFALL","json":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL.json","graph_json":"https://pith.science/api/pith-number/75DM6RXX6MLSIVXOLI2V2OFALL/graph.json","events_json":"https://pith.science/api/pith-number/75DM6RXX6MLSIVXOLI2V2OFALL/events.json","paper":"https://pith.science/paper/75DM6RXX"},"agent_actions":{"view_html":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL","download_json":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL.json","view_paper":"https://pith.science/paper/75DM6RXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23881&json=true","fetch_graph":"https://pith.science/api/pith-number/75DM6RXX6MLSIVXOLI2V2OFALL/graph.json","fetch_events":"https://pith.science/api/pith-number/75DM6RXX6MLSIVXOLI2V2OFALL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL/action/storage_attestation","attest_author":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL/action/author_attestation","sign_citation":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL/action/citation_signature","submit_replication":"https://pith.science/pith/75DM6RXX6MLSIVXOLI2V2OFALL/action/replication_record"}},"created_at":"2026-06-24T00:14:29.236424+00:00","updated_at":"2026-06-24T00:14:29.236424+00:00"}