{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","short_pith_number":"pith:B2PU2M2Z","canonical_record":{"source":{"id":"2403.05060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"89fc5ae69b3f6744733bebcffa3c9f06e7bedb22356add265b29b99c616f42eb","abstract_canon_sha256":"a46dc5d8d8e5a2fb6a6a5f3c1ee1f97cb52ca8b52b1859eb2f43600fe35360ec"},"schema_version":"1.0"},"canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","source":{"kind":"arxiv","id":"2403.05060","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05060","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05060v3","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05060","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"B2PU2M2ZNNHX","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"B2PU2M2ZNNHXIFXQ","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"B2PU2M2Z","created_at":"2026-07-05T08:44:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","target":"record","payload":{"canonical_record":{"source":{"id":"2403.05060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"89fc5ae69b3f6744733bebcffa3c9f06e7bedb22356add265b29b99c616f42eb","abstract_canon_sha256":"a46dc5d8d8e5a2fb6a6a5f3c1ee1f97cb52ca8b52b1859eb2f43600fe35360ec"},"schema_version":"1.0"},"canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:12.517826Z","signature_b64":"j0W3VNOSp0ecvnPB2a+YqVG6fwJm9OZnsrQXb75teQemBnnHdhT/Q2N6NE7852Iovfk92b2Mk8VmTYouT6sGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","last_reissued_at":"2026-07-05T08:44:12.517285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:12.517285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.05060","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":"2026-07-05T08:44:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/v+gJi9gvosJtsfpqQR+oeOQ5bmAbTcz5hef89C2fWPpN2M0DTnpT+BikKC5qp7cTYjwhj1Y30TYhGD1Rqw+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:18.880457Z"},"content_sha256":"78becef5eb24729f9b9b2144bfda1cb512e6a05a348d1344681e1fb8a9996b55","schema_version":"1.0","event_id":"sha256:78becef5eb24729f9b9b2144bfda1cb512e6a05a348d1344681e1fb8a9996b55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Infusion Tuning for Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.MM","authors_text":"Hao Sun, Jiaqing Liu, Lanfen Lin, Xinyao Yu, Yen-Wei Chen, Yu Song","submitted_at":"2024-03-08T05:15:05Z","abstract_excerpt":"Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05060","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/2403.05060/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":"2026-07-05T08:44:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHwggMjglhuLDvoB4cF7N+yjQRVbG8uIIaMBysuHF9WfSLwi7j2vHJEg182S14eJayJfLOK+vPxow/5urPmgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:18.880981Z"},"content_sha256":"6af1ba69fcc0fe118203258bf687d6a28d06115daa4051b23e9b5ab9365beeb6","schema_version":"1.0","event_id":"sha256:6af1ba69fcc0fe118203258bf687d6a28d06115daa4051b23e9b5ab9365beeb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/bundle.json","state_url":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/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":"2026-08-09T04:57:18Z","links":{"resolver":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","bundle":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/bundle.json","state":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","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":"a46dc5d8d8e5a2fb6a6a5f3c1ee1f97cb52ca8b52b1859eb2f43600fe35360ec","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","title_canon_sha256":"89fc5ae69b3f6744733bebcffa3c9f06e7bedb22356add265b29b99c616f42eb"},"schema_version":"1.0","source":{"id":"2403.05060","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05060","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05060v3","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05060","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"B2PU2M2ZNNHX","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"B2PU2M2ZNNHXIFXQ","created_at":"2026-07-05T08:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"B2PU2M2Z","created_at":"2026-07-05T08:44:12Z"}],"graph_snapshots":[{"event_id":"sha256:6af1ba69fcc0fe118203258bf687d6a28d06115daa4051b23e9b5ab9365beeb6","target":"graph","created_at":"2026-07-05T08:44:12Z","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/2403.05060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoust","authors_text":"Hao Sun, Jiaqing Liu, Lanfen Lin, Xinyao Yu, Yen-Wei Chen, Yu Song","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","title":"Multimodal Infusion Tuning for Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05060","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":"sha256:78becef5eb24729f9b9b2144bfda1cb512e6a05a348d1344681e1fb8a9996b55","target":"record","created_at":"2026-07-05T08:44:12Z","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":"a46dc5d8d8e5a2fb6a6a5f3c1ee1f97cb52ca8b52b1859eb2f43600fe35360ec","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","title_canon_sha256":"89fc5ae69b3f6744733bebcffa3c9f06e7bedb22356add265b29b99c616f42eb"},"schema_version":"1.0","source":{"id":"2403.05060","kind":"arxiv","version":3}},"canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","first_computed_at":"2026-07-05T08:44:12.517285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:12.517285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0W3VNOSp0ecvnPB2a+YqVG6fwJm9OZnsrQXb75teQemBnnHdhT/Q2N6NE7852Iovfk92b2Mk8VmTYouT6sGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:12.517826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05060","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78becef5eb24729f9b9b2144bfda1cb512e6a05a348d1344681e1fb8a9996b55","sha256:6af1ba69fcc0fe118203258bf687d6a28d06115daa4051b23e9b5ab9365beeb6"],"state_sha256":"70fbb3d4a1f902146a6d963dacafc133d05f2372317f1c55c161ed58c266324a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"juQv7XtwnNYNY3TcEbbPO+NOZtGDaP+sqrtOmFDOzMXEn+IEpEowdcg9IfoqgNAgXehvk5Zbp1qZTnhCgL+kAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:57:18.884823Z","bundle_sha256":"a8f6dc64d6788f80b9ed0f67e4711794abec9fd6381f612f2a7b965bff856100"}}