{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4VDWM77NGHJTOYV5KKHMFY2HIG","short_pith_number":"pith:4VDWM77N","canonical_record":{"source":{"id":"2410.16261","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"384021ef382e534de4b50b887c771bf1a4bf910dd99e7c18196c369af8a46293","abstract_canon_sha256":"3d84875451bb17ca8fea8dda18a88d48e53145ac1e3994d30aff3f76aa89fd6d"},"schema_version":"1.0"},"canonical_sha256":"e547667fed31d33762bd528ec2e34741af18073ab94082f5fa4e08b5ae1443e1","source":{"kind":"arxiv","id":"2410.16261","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16261","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16261v3","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16261","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"4VDWM77NGHJT","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"4VDWM77NGHJTOYV5","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"4VDWM77N","created_at":"2026-07-05T09:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4VDWM77NGHJTOYV5KKHMFY2HIG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16261","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"384021ef382e534de4b50b887c771bf1a4bf910dd99e7c18196c369af8a46293","abstract_canon_sha256":"3d84875451bb17ca8fea8dda18a88d48e53145ac1e3994d30aff3f76aa89fd6d"},"schema_version":"1.0"},"canonical_sha256":"e547667fed31d33762bd528ec2e34741af18073ab94082f5fa4e08b5ae1443e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:33.423401Z","signature_b64":"svPUHS+2GtGLYrwaCfUAgVdsLSWDjt0tVihbi++Kg/kZ1rdaBxWXuIoOKyOxa7tQR3cERGvI3/CcOPMZJJ1HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e547667fed31d33762bd528ec2e34741af18073ab94082f5fa4e08b5ae1443e1","last_reissued_at":"2026-07-05T09:32:33.422898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:33.422898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16261","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHmqx+zLgiWYB7scyWzfPPB4TAnjXAxkYJvCZuHg/bZVaZaCJe7i2YWppDN4j84N+6oSs4+20AUmDpFXl61+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:16.572708Z"},"content_sha256":"5d127c12228e636fab9348a0cf2546304b9f41dc3191d68b70a2d8c023dc0e81","schema_version":"1.0","event_id":"sha256:5d127c12228e636fab9348a0cf2546304b9f41dc3191d68b70a2d8c023dc0e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4VDWM77NGHJTOYV5KKHMFY2HIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erfei Cui, Hao Tian, Jifeng Dai, Jinguo Zhu, Junjun He, Lewei Lu, Shenglong Ye, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yiming Ren, Yu Qiao, Zhangwei Gao, Zhe Chen","submitted_at":"2024-10-21T17:58:20Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a broad spectrum of domains. However, the large model scale and associated high computational costs pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices, thereby hindering their widespread application. In this work, we introduce Mini-InternVL, a series of MLLMs with parameters ranging from 1B to 4B, which achieves 90% of the performance with only 5% of the parameters. This significant improvement in efficiency and effectiveness makes o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16261","kind":"arxiv","version":3},"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/2410.16261/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kz3Vih/+CIW/8AaLdbwrAfp2VB+wqZ2Mkjqwnd8xsgaDDAsVWOGxUT+WXhiehNTDXzMYVx/wqakJDUX99sxLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:16.573200Z"},"content_sha256":"9f5d3dcc2886de5c07e4f12b1ce6465398392afc32eba6174991d73960d05fae","schema_version":"1.0","event_id":"sha256:9f5d3dcc2886de5c07e4f12b1ce6465398392afc32eba6174991d73960d05fae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/bundle.json","state_url":"https://pith.science/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/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":"2026-08-07T15:39:16Z","links":{"resolver":"https://pith.science/pith/4VDWM77NGHJTOYV5KKHMFY2HIG","bundle":"https://pith.science/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/bundle.json","state":"https://pith.science/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VDWM77NGHJTOYV5KKHMFY2HIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VDWM77NGHJTOYV5KKHMFY2HIG","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":"3d84875451bb17ca8fea8dda18a88d48e53145ac1e3994d30aff3f76aa89fd6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:58:20Z","title_canon_sha256":"384021ef382e534de4b50b887c771bf1a4bf910dd99e7c18196c369af8a46293"},"schema_version":"1.0","source":{"id":"2410.16261","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16261","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16261v3","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16261","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"4VDWM77NGHJT","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"4VDWM77NGHJTOYV5","created_at":"2026-07-05T09:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"4VDWM77N","created_at":"2026-07-05T09:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:9f5d3dcc2886de5c07e4f12b1ce6465398392afc32eba6174991d73960d05fae","target":"graph","created_at":"2026-07-05T09:32:33Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.16261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a broad spectrum of domains. However, the large model scale and associated high computational costs pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices, thereby hindering their widespread application. In this work, we introduce Mini-InternVL, a series of MLLMs with parameters ranging from 1B to 4B, which achieves 90% of the performance with only 5% of the parameters. This significant improvement in efficiency and effectiveness makes o","authors_text":"Erfei Cui, Hao Tian, Jifeng Dai, Jinguo Zhu, Junjun He, Lewei Lu, Shenglong Ye, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yiming Ren, Yu Qiao, Zhangwei Gao, Zhe Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:58:20Z","title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16261","kind":"arxiv","version":3},"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":"sha256:5d127c12228e636fab9348a0cf2546304b9f41dc3191d68b70a2d8c023dc0e81","target":"record","created_at":"2026-07-05T09:32:33Z","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":"3d84875451bb17ca8fea8dda18a88d48e53145ac1e3994d30aff3f76aa89fd6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:58:20Z","title_canon_sha256":"384021ef382e534de4b50b887c771bf1a4bf910dd99e7c18196c369af8a46293"},"schema_version":"1.0","source":{"id":"2410.16261","kind":"arxiv","version":3}},"canonical_sha256":"e547667fed31d33762bd528ec2e34741af18073ab94082f5fa4e08b5ae1443e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e547667fed31d33762bd528ec2e34741af18073ab94082f5fa4e08b5ae1443e1","first_computed_at":"2026-07-05T09:32:33.422898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:33.422898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"svPUHS+2GtGLYrwaCfUAgVdsLSWDjt0tVihbi++Kg/kZ1rdaBxWXuIoOKyOxa7tQR3cERGvI3/CcOPMZJJ1HAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:33.423401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16261","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d127c12228e636fab9348a0cf2546304b9f41dc3191d68b70a2d8c023dc0e81","sha256:9f5d3dcc2886de5c07e4f12b1ce6465398392afc32eba6174991d73960d05fae"],"state_sha256":"c4a67447f052393ffc639b06fc784f3f312f19839c58a7203d903620c1942c28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBYgp3haXC/WqBvomal7LTO9wTzYd8ybWna2ApsLH1WjwpjD3tKfDblqAxyjL9AsOpgBpDxfrCnl3Jj3cC7TCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:39:16.577334Z","bundle_sha256":"af8609839bf2fd6b9232d3cb08b35da9276fc9feedf6e15e26796ebafa459241"}}