{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BZE7JMLA3E7FAAFKGNJEQWMS3V","short_pith_number":"pith:BZE7JMLA","canonical_record":{"source":{"id":"2410.16236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:41:28Z","cross_cats_sorted":[],"title_canon_sha256":"8c086d9421deaa34d7e2650fe44f2dbefbfc1f80afc287674e34ae005b0a5504","abstract_canon_sha256":"841fdaf5d72faee39d2b2bec8693c7715d15bd942b69a8bb1f4421c1723e7962"},"schema_version":"1.0"},"canonical_sha256":"0e49f4b160d93e5000aa3352485992dd614182305107bea2b8959f5fc55b4ba4","source":{"kind":"arxiv","id":"2410.16236","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16236","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16236v3","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16236","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"BZE7JMLA3E7F","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_16","alias_value":"BZE7JMLA3E7FAAFK","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_8","alias_value":"BZE7JMLA","created_at":"2026-07-05T11:31:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BZE7JMLA3E7FAAFKGNJEQWMS3V","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:41:28Z","cross_cats_sorted":[],"title_canon_sha256":"8c086d9421deaa34d7e2650fe44f2dbefbfc1f80afc287674e34ae005b0a5504","abstract_canon_sha256":"841fdaf5d72faee39d2b2bec8693c7715d15bd942b69a8bb1f4421c1723e7962"},"schema_version":"1.0"},"canonical_sha256":"0e49f4b160d93e5000aa3352485992dd614182305107bea2b8959f5fc55b4ba4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:02.825675Z","signature_b64":"r3PQys4dC6sSGeKQWQPycRfsW+6zqKkUYqhskJ9GjCVyVH1WebeeLmpf7iBy5A+fS9fev8r29uFytDlaqjRGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e49f4b160d93e5000aa3352485992dd614182305107bea2b8959f5fc55b4ba4","last_reissued_at":"2026-07-05T11:31:02.825124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:02.825124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16236","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":"2026-07-05T11:31:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/7f3HwJN0LBqriSqYoRURgM53jK+VNkh9mLHI/nrNL6Srx1c73tAv/eO8d61/jdFXgsfsqwv59cwMo3FP6BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:31:52.669499Z"},"content_sha256":"1afca52b259288ebbc5ecaa348ae22012e2c6a0073822b28a11a6359f9cbdb82","schema_version":"1.0","event_id":"sha256:1afca52b259288ebbc5ecaa348ae22012e2c6a0073822b28a11a6359f9cbdb82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BZE7JMLA3E7FAAFKGNJEQWMS3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-KD: A Framework of Distilling Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Tong, Chengjie Wang, Haoyang He, Jiangning Zhang, Xiang Bai, Xinwei He, Yong Liu, Yuxuan Cai, Zhenye Gan, Zhucun Xue","submitted_at":"2024-10-21T17:41:28Z","abstract_excerpt":"The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the increasing model size and computational complexity of large-scale MLLMs (l-MLLMs) limit their use in resource-constrained scenarios. Although small-scale MLLMs (s-MLLMs) are designed to reduce computational costs, they typically suffer from performance degradation. To mitigate this limitation, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLMs to s-MLLMs. Specifically, we introduce Multimodal Di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16236","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/2410.16236/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":"2026-07-05T11:31:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mq/z2FQd8Xlsu9dbJXiCpJPxR8UtgE6DkjKtscXpViN/VG/fsRo50n0TFZWwMQ1og7P17CA2AQbHxVybOCr4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:31:52.670044Z"},"content_sha256":"20088d91ef4fb8e21d278f8cc234f020a94cb600ab9e56eb20d64a6644ea3dd3","schema_version":"1.0","event_id":"sha256:20088d91ef4fb8e21d278f8cc234f020a94cb600ab9e56eb20d64a6644ea3dd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/bundle.json","state_url":"https://pith.science/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/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":"2026-08-09T22:31:52Z","links":{"resolver":"https://pith.science/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V","bundle":"https://pith.science/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/bundle.json","state":"https://pith.science/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZE7JMLA3E7FAAFKGNJEQWMS3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BZE7JMLA3E7FAAFKGNJEQWMS3V","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":"841fdaf5d72faee39d2b2bec8693c7715d15bd942b69a8bb1f4421c1723e7962","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:41:28Z","title_canon_sha256":"8c086d9421deaa34d7e2650fe44f2dbefbfc1f80afc287674e34ae005b0a5504"},"schema_version":"1.0","source":{"id":"2410.16236","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16236","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16236v3","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16236","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"BZE7JMLA3E7F","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_16","alias_value":"BZE7JMLA3E7FAAFK","created_at":"2026-07-05T11:31:02Z"},{"alias_kind":"pith_short_8","alias_value":"BZE7JMLA","created_at":"2026-07-05T11:31:02Z"}],"graph_snapshots":[{"event_id":"sha256:20088d91ef4fb8e21d278f8cc234f020a94cb600ab9e56eb20d64a6644ea3dd3","target":"graph","created_at":"2026-07-05T11:31:02Z","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/2410.16236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the increasing model size and computational complexity of large-scale MLLMs (l-MLLMs) limit their use in resource-constrained scenarios. Although small-scale MLLMs (s-MLLMs) are designed to reduce computational costs, they typically suffer from performance degradation. To mitigate this limitation, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLMs to s-MLLMs. Specifically, we introduce Multimodal Di","authors_text":"Ao Tong, Chengjie Wang, Haoyang He, Jiangning Zhang, Xiang Bai, Xinwei He, Yong Liu, Yuxuan Cai, Zhenye Gan, Zhucun Xue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:41:28Z","title":"LLaVA-KD: A Framework of Distilling Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16236","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":"sha256:1afca52b259288ebbc5ecaa348ae22012e2c6a0073822b28a11a6359f9cbdb82","target":"record","created_at":"2026-07-05T11:31:02Z","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":"841fdaf5d72faee39d2b2bec8693c7715d15bd942b69a8bb1f4421c1723e7962","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:41:28Z","title_canon_sha256":"8c086d9421deaa34d7e2650fe44f2dbefbfc1f80afc287674e34ae005b0a5504"},"schema_version":"1.0","source":{"id":"2410.16236","kind":"arxiv","version":3}},"canonical_sha256":"0e49f4b160d93e5000aa3352485992dd614182305107bea2b8959f5fc55b4ba4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e49f4b160d93e5000aa3352485992dd614182305107bea2b8959f5fc55b4ba4","first_computed_at":"2026-07-05T11:31:02.825124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:02.825124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3PQys4dC6sSGeKQWQPycRfsW+6zqKkUYqhskJ9GjCVyVH1WebeeLmpf7iBy5A+fS9fev8r29uFytDlaqjRGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:02.825675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16236","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1afca52b259288ebbc5ecaa348ae22012e2c6a0073822b28a11a6359f9cbdb82","sha256:20088d91ef4fb8e21d278f8cc234f020a94cb600ab9e56eb20d64a6644ea3dd3"],"state_sha256":"96a21f6d77686f0611e4d8e6daec6b263f5cc9f94d3ed2c1c4835590ad086dd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVhpGGUuqvOWuXAseoOy0OV1kis0fbKKszG62T9j+QuI3z5oxYqa/QgcwSFvAMo1aKfamUyFShchCwV8yIKVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:31:52.674558Z","bundle_sha256":"d019c50f17bdb58c2f61e315bbe8f247a043fa5afbc309f696f09502d2a86bc9"}}