{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:THFGDCQQCYXN2IDPEONGMHW3MP","short_pith_number":"pith:THFGDCQQ","schema_version":"1.0","canonical_sha256":"99ca618a10162edd206f239a661edb63fdbdf9e6898a63238e3ec8f3179d778e","source":{"kind":"arxiv","id":"2411.10640","version":1},"attestation_state":"computed","paper":{"title":"BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Boheng Chen, Cheng Chen, Guanxin Tan, Han Xiao, Hongsheng Li, Hui Tan, Lei Wu, Liuyang Bian, Long Liu, Renshou Wu, Rui Hu, Shuai Ren, Xiaoxin Chen, Xudong Lu, Yafei Wen, Yan Hu, Yanzhou Yang, Yina Xie, Yinghao Chen, Yi Zeng, Zhaoxiong Wang","submitted_at":"2024-11-16T00:14:51Z","abstract_excerpt":"The emergence and growing popularity of multimodal large language models (MLLMs) have significant potential to enhance various aspects of daily life, from improving communication to facilitating learning and problem-solving. Mobile phones, as essential daily companions, represent the most effective and accessible deployment platform for MLLMs, enabling seamless integration into everyday tasks. However, deploying MLLMs on mobile phones presents challenges due to limitations in memory size and computational capability, making it difficult to achieve smooth and real-time processing without extens"},"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":"2411.10640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T00:14:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4800c0b6f5db5cb7df438ff4cc93747e12a0e42584360c2895242364178d3842","abstract_canon_sha256":"f791eb1d22280be9cbd03d173f66b3eeb4c247ea6537fda33fd69b8779d3ff99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:19.821884Z","signature_b64":"RBFDn5T8XNgatri/AYgF575kcq7B7VmJNQ0I2SFM0uBsQyNK+/AfK6mJ6r06IVyk0etqxiNoiw0ek4uwBbcoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99ca618a10162edd206f239a661edb63fdbdf9e6898a63238e3ec8f3179d778e","last_reissued_at":"2026-07-05T09:36:19.821393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:19.821393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Boheng Chen, Cheng Chen, Guanxin Tan, Han Xiao, Hongsheng Li, Hui Tan, Lei Wu, Liuyang Bian, Long Liu, Renshou Wu, Rui Hu, Shuai Ren, Xiaoxin Chen, Xudong Lu, Yafei Wen, Yan Hu, Yanzhou Yang, Yina Xie, Yinghao Chen, Yi Zeng, Zhaoxiong Wang","submitted_at":"2024-11-16T00:14:51Z","abstract_excerpt":"The emergence and growing popularity of multimodal large language models (MLLMs) have significant potential to enhance various aspects of daily life, from improving communication to facilitating learning and problem-solving. Mobile phones, as essential daily companions, represent the most effective and accessible deployment platform for MLLMs, enabling seamless integration into everyday tasks. However, deploying MLLMs on mobile phones presents challenges due to limitations in memory size and computational capability, making it difficult to achieve smooth and real-time processing without extens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10640","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/2411.10640/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":"2411.10640","created_at":"2026-07-05T09:36:19.821459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10640v1","created_at":"2026-07-05T09:36:19.821459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10640","created_at":"2026-07-05T09:36:19.821459+00:00"},{"alias_kind":"pith_short_12","alias_value":"THFGDCQQCYXN","created_at":"2026-07-05T09:36:19.821459+00:00"},{"alias_kind":"pith_short_16","alias_value":"THFGDCQQCYXN2IDP","created_at":"2026-07-05T09:36:19.821459+00:00"},{"alias_kind":"pith_short_8","alias_value":"THFGDCQQ","created_at":"2026-07-05T09:36:19.821459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP","json":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP.json","graph_json":"https://pith.science/api/pith-number/THFGDCQQCYXN2IDPEONGMHW3MP/graph.json","events_json":"https://pith.science/api/pith-number/THFGDCQQCYXN2IDPEONGMHW3MP/events.json","paper":"https://pith.science/paper/THFGDCQQ"},"agent_actions":{"view_html":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP","download_json":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP.json","view_paper":"https://pith.science/paper/THFGDCQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10640&json=true","fetch_graph":"https://pith.science/api/pith-number/THFGDCQQCYXN2IDPEONGMHW3MP/graph.json","fetch_events":"https://pith.science/api/pith-number/THFGDCQQCYXN2IDPEONGMHW3MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP/action/storage_attestation","attest_author":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP/action/author_attestation","sign_citation":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP/action/citation_signature","submit_replication":"https://pith.science/pith/THFGDCQQCYXN2IDPEONGMHW3MP/action/replication_record"}},"created_at":"2026-07-05T09:36:19.821459+00:00","updated_at":"2026-07-05T09:36:19.821459+00:00"}