{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGCHNW4WFRH3NEX3TCYMCI6IFW","short_pith_number":"pith:JGCHNW4W","schema_version":"1.0","canonical_sha256":"498476db962c4fb692fb98b0c123c82daa72352a89a1ae61e560cc1cb1a5c5e3","source":{"kind":"arxiv","id":"2504.05288","version":2},"attestation_state":"computed","paper":{"title":"Seeking and Updating with Live Visual Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Dongping Chen, Mingyang Fu, Philip S. Yu, Ranjay Krishna, Yao Wan, Yuyang Peng, Zetong Zhou, Zhou Zhao","submitted_at":"2025-04-07T17:39:31Z","abstract_excerpt":"The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models (MLLMs), which automate many tasks, struggle to stay current, limited by the cutoff dates in their fixed training datasets. To quantify this stagnation, we introduce LiveVQA, the first-of-its-kind dataset featuring 107,143 samples and 12 categories data specifically designed to support research in both seeking and updating with live visual knowledge. Drawing fro"},"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":"2504.05288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T17:39:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2c9469bf06cca79e801356d148c5b4738346eecd3e17713f29c8bc5f8e2bc248","abstract_canon_sha256":"346ef76ff0218015578c7427795c501f1a00f194a6321dc59c641bd132c0a8be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:57.315967Z","signature_b64":"DZFAnJTJ09hjBs8C8hurijwME7of7cfanw6okSNvS8S8l6iG3XJbmP0oCJOIwxtKHDKTbrw02TdGcMYKw6hlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498476db962c4fb692fb98b0c123c82daa72352a89a1ae61e560cc1cb1a5c5e3","last_reissued_at":"2026-07-05T11:29:57.315487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:57.315487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeking and Updating with Live Visual Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Dongping Chen, Mingyang Fu, Philip S. Yu, Ranjay Krishna, Yao Wan, Yuyang Peng, Zetong Zhou, Zhou Zhao","submitted_at":"2025-04-07T17:39:31Z","abstract_excerpt":"The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models (MLLMs), which automate many tasks, struggle to stay current, limited by the cutoff dates in their fixed training datasets. To quantify this stagnation, we introduce LiveVQA, the first-of-its-kind dataset featuring 107,143 samples and 12 categories data specifically designed to support research in both seeking and updating with live visual knowledge. Drawing fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05288","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/2504.05288/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":"2504.05288","created_at":"2026-07-05T11:29:57.315547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05288v2","created_at":"2026-07-05T11:29:57.315547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05288","created_at":"2026-07-05T11:29:57.315547+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGCHNW4WFRH3","created_at":"2026-07-05T11:29:57.315547+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGCHNW4WFRH3NEX3","created_at":"2026-07-05T11:29:57.315547+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGCHNW4W","created_at":"2026-07-05T11:29:57.315547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31504","citing_title":"SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28344","citing_title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20486","citing_title":"ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19264","citing_title":"DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14029","citing_title":"POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW","json":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW.json","graph_json":"https://pith.science/api/pith-number/JGCHNW4WFRH3NEX3TCYMCI6IFW/graph.json","events_json":"https://pith.science/api/pith-number/JGCHNW4WFRH3NEX3TCYMCI6IFW/events.json","paper":"https://pith.science/paper/JGCHNW4W"},"agent_actions":{"view_html":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW","download_json":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW.json","view_paper":"https://pith.science/paper/JGCHNW4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05288&json=true","fetch_graph":"https://pith.science/api/pith-number/JGCHNW4WFRH3NEX3TCYMCI6IFW/graph.json","fetch_events":"https://pith.science/api/pith-number/JGCHNW4WFRH3NEX3TCYMCI6IFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW/action/storage_attestation","attest_author":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW/action/author_attestation","sign_citation":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW/action/citation_signature","submit_replication":"https://pith.science/pith/JGCHNW4WFRH3NEX3TCYMCI6IFW/action/replication_record"}},"created_at":"2026-07-05T11:29:57.315547+00:00","updated_at":"2026-07-05T11:29:57.315547+00:00"}