{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UQNYXUYJ4MQCBMJFVLA4OMZ376","short_pith_number":"pith:UQNYXUYJ","canonical_record":{"source":{"id":"2508.10955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T07:25:45Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"5496accd0843682688365f09bf54f5d0e51bb600bf5c1bbcfb2c71db516e802c","abstract_canon_sha256":"a51ea29d43e64f777060861462fec1e2b207aa741d5b1bbc1a824c18f9366609"},"schema_version":"1.0"},"canonical_sha256":"a41b8bd309e32020b125aac1c7333bff8e28e79b914057142d1b2c5addc35549","source":{"kind":"arxiv","id":"2508.10955","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10955","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10955v1","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10955","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"UQNYXUYJ4MQC","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"UQNYXUYJ4MQCBMJF","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"UQNYXUYJ","created_at":"2026-07-05T11:54:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UQNYXUYJ4MQCBMJFVLA4OMZ376","target":"record","payload":{"canonical_record":{"source":{"id":"2508.10955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T07:25:45Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"5496accd0843682688365f09bf54f5d0e51bb600bf5c1bbcfb2c71db516e802c","abstract_canon_sha256":"a51ea29d43e64f777060861462fec1e2b207aa741d5b1bbc1a824c18f9366609"},"schema_version":"1.0"},"canonical_sha256":"a41b8bd309e32020b125aac1c7333bff8e28e79b914057142d1b2c5addc35549","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:16.175172Z","signature_b64":"rtWmIUrZ5WHaO9dzocE2NlKaa28oCIOXlD3/kgNu14b8QtHOe4dJmDldpCLJW/r8tyQ+O5d0RalhHESTjkXjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a41b8bd309e32020b125aac1c7333bff8e28e79b914057142d1b2c5addc35549","last_reissued_at":"2026-07-05T11:54:16.174711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:16.174711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.10955","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":"2026-07-05T11:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6fRlp2miNepRO3De9i87Hh+NPgMjWLCnkuyvTqCV5fpBgl1zMP9RnjyidhMnwBUp8Qhq0IN4h8G+tZNFgJzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:13:17.974016Z"},"content_sha256":"5671b4dcbcc47149ec25b4c11777cdf12a555d39c93b84d93b9af75b51c0cf7e","schema_version":"1.0","event_id":"sha256:5671b4dcbcc47149ec25b4c11777cdf12a555d39c93b84d93b9af75b51c0cf7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UQNYXUYJ4MQCBMJFVLA4OMZ376","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Feng Tian, Jiahao Nie, Qinghua Zheng, Shijian Lu, Wenbin An, Yaqiang Wu","submitted_at":"2025-08-14T07:25:45Z","abstract_excerpt":"By integrating the perception capabilities of multimodal encoders with the generative power of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), exemplified by GPT-4V, have achieved great success in various multimodal tasks, pointing toward a promising pathway to artificial general intelligence. Despite this progress, the limited quality of multimodal data, poor performance on many complex downstream tasks, and inadequate evaluation protocols continue to hinder the reliability and broader applicability of MLLMs across diverse domains. Inspired by the human ability to leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10955","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.10955/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":"2026-07-05T11:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGDdADnCpVBO7UnYLF+Y9J4BYa+Wf2sndYqJrN4nRwwUg9+5PpAzeyFtsvAh7vBiAVv2TelXS5FAqwDMxL0oDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:13:17.974514Z"},"content_sha256":"e46b33ca9fc381fdb25ab5aa8cdd1a986739aacc5aade20dc3e0f274059bf12b","schema_version":"1.0","event_id":"sha256:e46b33ca9fc381fdb25ab5aa8cdd1a986739aacc5aade20dc3e0f274059bf12b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/bundle.json","state_url":"https://pith.science/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/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":"2026-08-23T01:13:17Z","links":{"resolver":"https://pith.science/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376","bundle":"https://pith.science/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/bundle.json","state":"https://pith.science/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQNYXUYJ4MQCBMJFVLA4OMZ376/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UQNYXUYJ4MQCBMJFVLA4OMZ376","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":"a51ea29d43e64f777060861462fec1e2b207aa741d5b1bbc1a824c18f9366609","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T07:25:45Z","title_canon_sha256":"5496accd0843682688365f09bf54f5d0e51bb600bf5c1bbcfb2c71db516e802c"},"schema_version":"1.0","source":{"id":"2508.10955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10955","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10955v1","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10955","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"UQNYXUYJ4MQC","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"UQNYXUYJ4MQCBMJF","created_at":"2026-07-05T11:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"UQNYXUYJ","created_at":"2026-07-05T11:54:16Z"}],"graph_snapshots":[{"event_id":"sha256:e46b33ca9fc381fdb25ab5aa8cdd1a986739aacc5aade20dc3e0f274059bf12b","target":"graph","created_at":"2026-07-05T11:54:16Z","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/2508.10955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By integrating the perception capabilities of multimodal encoders with the generative power of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), exemplified by GPT-4V, have achieved great success in various multimodal tasks, pointing toward a promising pathway to artificial general intelligence. Despite this progress, the limited quality of multimodal data, poor performance on many complex downstream tasks, and inadequate evaluation protocols continue to hinder the reliability and broader applicability of MLLMs across diverse domains. Inspired by the human ability to leve","authors_text":"Feng Tian, Jiahao Nie, Qinghua Zheng, Shijian Lu, Wenbin An, Yaqiang Wu","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T07:25:45Z","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10955","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":"sha256:5671b4dcbcc47149ec25b4c11777cdf12a555d39c93b84d93b9af75b51c0cf7e","target":"record","created_at":"2026-07-05T11:54:16Z","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":"a51ea29d43e64f777060861462fec1e2b207aa741d5b1bbc1a824c18f9366609","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T07:25:45Z","title_canon_sha256":"5496accd0843682688365f09bf54f5d0e51bb600bf5c1bbcfb2c71db516e802c"},"schema_version":"1.0","source":{"id":"2508.10955","kind":"arxiv","version":1}},"canonical_sha256":"a41b8bd309e32020b125aac1c7333bff8e28e79b914057142d1b2c5addc35549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a41b8bd309e32020b125aac1c7333bff8e28e79b914057142d1b2c5addc35549","first_computed_at":"2026-07-05T11:54:16.174711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:16.174711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtWmIUrZ5WHaO9dzocE2NlKaa28oCIOXlD3/kgNu14b8QtHOe4dJmDldpCLJW/r8tyQ+O5d0RalhHESTjkXjDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:16.175172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5671b4dcbcc47149ec25b4c11777cdf12a555d39c93b84d93b9af75b51c0cf7e","sha256:e46b33ca9fc381fdb25ab5aa8cdd1a986739aacc5aade20dc3e0f274059bf12b"],"state_sha256":"b3e82d8ba23c3d12ee97d9426811c4cc8a86691c44a379d2520ca7ebdcf5b791"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJH/u6yWZ/dVcBCkw4HoEFLhFsqQWvJ5lPSxMEIvpnuDNSgrgu3S62+Jsde4lOd1XZUY7IOptiNcaHltZd9JAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T01:13:17.979542Z","bundle_sha256":"1a495946187fb7a1ee47a43f78bfcfa5a9de37885066b711bd6228910458b114"}}