{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G5ZECB57OBTUI6HJDFVZDIN2AL","short_pith_number":"pith:G5ZECB57","canonical_record":{"source":{"id":"2311.07594","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T09:51:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"title_canon_sha256":"28e52f44bd00f9bd13fd2e6033e6a8a8fb3d24710f9b9a52755f1ccda681f616","abstract_canon_sha256":"401332a130b16f67e89a7d564f860527b0fe1fb86c118bd1133eb2871fc6d098"},"schema_version":"1.0"},"canonical_sha256":"37724107bf70674478e9196b91a1ba02d573c05a6230dd650f7e7fce7f4ceee4","source":{"kind":"arxiv","id":"2311.07594","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07594","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07594v3","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07594","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZECB57OBTU","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZECB57OBTUI6HJ","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZECB57","created_at":"2026-07-05T09:58:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G5ZECB57OBTUI6HJDFVZDIN2AL","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07594","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T09:51:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"title_canon_sha256":"28e52f44bd00f9bd13fd2e6033e6a8a8fb3d24710f9b9a52755f1ccda681f616","abstract_canon_sha256":"401332a130b16f67e89a7d564f860527b0fe1fb86c118bd1133eb2871fc6d098"},"schema_version":"1.0"},"canonical_sha256":"37724107bf70674478e9196b91a1ba02d573c05a6230dd650f7e7fce7f4ceee4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:17.311433Z","signature_b64":"Ve/Ab0cxX0HbKS8cEwEpULrJZVwiX6zP91Bm9WaQ5XEWa3FBBwpuRmiqIJd+a8RrusqLtJQn4tPYkd0zl6XIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37724107bf70674478e9196b91a1ba02d573c05a6230dd650f7e7fce7f4ceee4","last_reissued_at":"2026-07-05T09:58:17.310908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:17.310908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07594","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":"2026-07-05T09:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FeWlXXhht1744AJb+7EqbP1/mMsD5h7hXwPQuk9/9JS+Pz6k75SfYTD8VCZPjQDCJlEruUIKUBgpcqHBX4D+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:30:53.844633Z"},"content_sha256":"6083c170dfcf6e61d6521086f16ebd6002eb3912056b004a236ae08f73507978","schema_version":"1.0","event_id":"sha256:6083c170dfcf6e61d6521086f16ebd6002eb3912056b004a236ae08f73507978"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G5ZECB57OBTUI6HJDFVZDIN2AL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Jie Yu, Jun Ma, Shan Zhao, Shasha Li, Shezheng Song, Weimin Zhang, Xiaoguang Mao, Xiaopeng Li","submitted_at":"2023-11-10T09:51:24Z","abstract_excerpt":"We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in addressing the semantic gap in multimodal data, which may lead to erroneous outputs, posing potential risks to society. Selecting the appropriate modality alignment metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07594","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/2311.07594/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":"2026-07-05T09:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6TS0FMjCXZMR1bf1PZ9CCVH9eNqtMi5xdFvAPLRzY6Rl6LPUyt1PG1Z7r3G+2awHy6jFbXF41SyF/vn3jGB/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:30:53.845149Z"},"content_sha256":"d7e93f84ed7faaea3321699c4576eae812a89c5fbd77ef2a26afe6ff1e003a2f","schema_version":"1.0","event_id":"sha256:d7e93f84ed7faaea3321699c4576eae812a89c5fbd77ef2a26afe6ff1e003a2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/bundle.json","state_url":"https://pith.science/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/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":"2026-08-05T22:30:53Z","links":{"resolver":"https://pith.science/pith/G5ZECB57OBTUI6HJDFVZDIN2AL","bundle":"https://pith.science/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/bundle.json","state":"https://pith.science/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5ZECB57OBTUI6HJDFVZDIN2AL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G5ZECB57OBTUI6HJDFVZDIN2AL","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":"401332a130b16f67e89a7d564f860527b0fe1fb86c118bd1133eb2871fc6d098","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T09:51:24Z","title_canon_sha256":"28e52f44bd00f9bd13fd2e6033e6a8a8fb3d24710f9b9a52755f1ccda681f616"},"schema_version":"1.0","source":{"id":"2311.07594","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07594","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07594v3","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07594","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZECB57OBTU","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZECB57OBTUI6HJ","created_at":"2026-07-05T09:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZECB57","created_at":"2026-07-05T09:58:17Z"}],"graph_snapshots":[{"event_id":"sha256:d7e93f84ed7faaea3321699c4576eae812a89c5fbd77ef2a26afe6ff1e003a2f","target":"graph","created_at":"2026-07-05T09:58:17Z","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/2311.07594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in addressing the semantic gap in multimodal data, which may lead to erroneous outputs, posing potential risks to society. Selecting the appropriate modality alignment metho","authors_text":"Jie Yu, Jun Ma, Shan Zhao, Shasha Li, Shezheng Song, Weimin Zhang, Xiaoguang Mao, Xiaopeng Li","cross_cats":["cs.AI","cs.CV","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T09:51:24Z","title":"How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07594","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":"sha256:6083c170dfcf6e61d6521086f16ebd6002eb3912056b004a236ae08f73507978","target":"record","created_at":"2026-07-05T09:58:17Z","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":"401332a130b16f67e89a7d564f860527b0fe1fb86c118bd1133eb2871fc6d098","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T09:51:24Z","title_canon_sha256":"28e52f44bd00f9bd13fd2e6033e6a8a8fb3d24710f9b9a52755f1ccda681f616"},"schema_version":"1.0","source":{"id":"2311.07594","kind":"arxiv","version":3}},"canonical_sha256":"37724107bf70674478e9196b91a1ba02d573c05a6230dd650f7e7fce7f4ceee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37724107bf70674478e9196b91a1ba02d573c05a6230dd650f7e7fce7f4ceee4","first_computed_at":"2026-07-05T09:58:17.310908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:17.310908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ve/Ab0cxX0HbKS8cEwEpULrJZVwiX6zP91Bm9WaQ5XEWa3FBBwpuRmiqIJd+a8RrusqLtJQn4tPYkd0zl6XIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:17.311433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07594","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6083c170dfcf6e61d6521086f16ebd6002eb3912056b004a236ae08f73507978","sha256:d7e93f84ed7faaea3321699c4576eae812a89c5fbd77ef2a26afe6ff1e003a2f"],"state_sha256":"e7214fc76fb8a7f950bc242a0124ce70c9f615a9a430cc4ad09910f433c2b376"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGhuuvsqYIqKhbyLWZfTw+4lpVJakpV9ytAUnC9lUsrF2zNbVAvrsVRpIgktw+O/DhWx0iHST6pNWY+FOoXPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:30:53.850124Z","bundle_sha256":"3fddc68c27b4a1ec9fdb3294b302fe82dcec239ef8299d2c916b18cef914fad5"}}