{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SCPEKNYM2KZORBN34L53N2ZXQI","short_pith_number":"pith:SCPEKNYM","canonical_record":{"source":{"id":"2402.03766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b9c58045de68a8b2907ac0d45e29242e04429d9fa6940472a6ac564a360e02","abstract_canon_sha256":"7eb8e16f991b71830f382d088f0cf1c5c5829439efb21b87c2952af69febfcb7"},"schema_version":"1.0"},"canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","source":{"kind":"arxiv","id":"2402.03766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03766","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03766v1","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03766","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"SCPEKNYM2KZO","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"SCPEKNYM2KZORBN3","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"SCPEKNYM","created_at":"2026-05-18T15:20:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SCPEKNYM2KZORBN34L53N2ZXQI","target":"record","payload":{"canonical_record":{"source":{"id":"2402.03766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b9c58045de68a8b2907ac0d45e29242e04429d9fa6940472a6ac564a360e02","abstract_canon_sha256":"7eb8e16f991b71830f382d088f0cf1c5c5829439efb21b87c2952af69febfcb7"},"schema_version":"1.0"},"canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T15:20:59.326796Z","signature_b64":"BRBgDR1TojGpgLy1UI2OwaCZRFgZXm9tOujzbNVQ1XCMVyPVJSaR0YheA0Q15mp59FRR35O6821UjclnattvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","last_reissued_at":"2026-05-18T15:20:59.324347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T15:20:59.324347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.03766","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T15:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNgZ+l9/3Y7MCJwIPjgYMiNTrBOD+MtEsP+hTtyrCFJsE2LOhzfsIGaZADt0uf2DhA22JMom0YUFyNf2trt1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T04:23:52.531613Z"},"content_sha256":"ae98ab8553ceefac051adcd87440704a71b40abdae8cb42a5e90da4e148e2534","schema_version":"1.0","event_id":"sha256:ae98ab8553ceefac051adcd87440704a71b40abdae8cb42a5e90da4e148e2534"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SCPEKNYM2KZORBN34L53N2ZXQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chunhua Shen, Fei Wei, Limeng Qiao, Shuang Xu, Xiangxiang Chu, Xiaofei Sun, Xinyang Lin, Xinyu Zhang, Yang Yang, Yiming Hu","submitted_at":"2024-02-06T07:16:36Z","abstract_excerpt":"We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03766","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T15:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IxCHGDaAz7U1d1tnsFye/ReZSd5T5n5a+RR/f6GvAitBmkdHiqkcHPLTN/4PuPaYxkVVDwaLxCeThwPorfnPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T04:23:52.532239Z"},"content_sha256":"8147f7283a1e9d7be2996a432efd2eedf08a36bf67858f8a32e58ccdc225428b","schema_version":"1.0","event_id":"sha256:8147f7283a1e9d7be2996a432efd2eedf08a36bf67858f8a32e58ccdc225428b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/bundle.json","state_url":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCPEKNYM2KZORBN34L53N2ZXQI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T04:23:52Z","links":{"resolver":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI","bundle":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/bundle.json","state":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCPEKNYM2KZORBN34L53N2ZXQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SCPEKNYM2KZORBN34L53N2ZXQI","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":"7eb8e16f991b71830f382d088f0cf1c5c5829439efb21b87c2952af69febfcb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","title_canon_sha256":"84b9c58045de68a8b2907ac0d45e29242e04429d9fa6940472a6ac564a360e02"},"schema_version":"1.0","source":{"id":"2402.03766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03766","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03766v1","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03766","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"SCPEKNYM2KZO","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"SCPEKNYM2KZORBN3","created_at":"2026-05-18T15:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"SCPEKNYM","created_at":"2026-05-18T15:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:8147f7283a1e9d7be2996a432efd2eedf08a36bf67858f8a32e58ccdc225428b","target":"graph","created_at":"2026-05-18T15:20:59Z","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"},"paper":{"abstract_excerpt":"We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/M","authors_text":"Bo Zhang, Chunhua Shen, Fei Wei, Limeng Qiao, Shuang Xu, Xiangxiang Chu, Xiaofei Sun, Xinyang Lin, Xinyu Zhang, Yang Yang, Yiming Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03766","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:ae98ab8553ceefac051adcd87440704a71b40abdae8cb42a5e90da4e148e2534","target":"record","created_at":"2026-05-18T15:20:59Z","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":"7eb8e16f991b71830f382d088f0cf1c5c5829439efb21b87c2952af69febfcb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","title_canon_sha256":"84b9c58045de68a8b2907ac0d45e29242e04429d9fa6940472a6ac564a360e02"},"schema_version":"1.0","source":{"id":"2402.03766","kind":"arxiv","version":1}},"canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","first_computed_at":"2026-05-18T15:20:59.324347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T15:20:59.324347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRBgDR1TojGpgLy1UI2OwaCZRFgZXm9tOujzbNVQ1XCMVyPVJSaR0YheA0Q15mp59FRR35O6821UjclnattvBg==","signature_status":"signed_v1","signed_at":"2026-05-18T15:20:59.326796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae98ab8553ceefac051adcd87440704a71b40abdae8cb42a5e90da4e148e2534","sha256:8147f7283a1e9d7be2996a432efd2eedf08a36bf67858f8a32e58ccdc225428b"],"state_sha256":"0b42b739bd546292ad9b642ec49d89532465439574d84eca452ee55d15e7845f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1rs13+X0+JdjZmmLrZdItYRusJ+wPm0vnuXMP/AxXURKeTxjQ+mbR+32+/LuQ7uWk+8AriYb21ZyVHl7S/IlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T04:23:52.534122Z","bundle_sha256":"ea1d6fd736f31224ec72904a12cee376719e0e57feda36dd7f7069222d9b8741"}}