{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GKDRKGKIZCZYGHB5IRCSTTVQ3Q","short_pith_number":"pith:GKDRKGKI","canonical_record":{"source":{"id":"2401.10727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T14:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"ddacf768f72278dea085cc983538b9e3ee188879e16d694443a48e20d40fc554","abstract_canon_sha256":"19e9e6b5d3930b8eab368eb04dcab688ddfe1a834dbcca6b47172490a4b199a0"},"schema_version":"1.0"},"canonical_sha256":"3287151948c8b3831c3d444529ceb0dc340140f2a28675e9be179924d29e9d14","source":{"kind":"arxiv","id":"2401.10727","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10727","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10727v3","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10727","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"GKDRKGKIZCZY","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_16","alias_value":"GKDRKGKIZCZYGHB5","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_8","alias_value":"GKDRKGKI","created_at":"2026-07-05T10:47:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GKDRKGKIZCZYGHB5IRCSTTVQ3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2401.10727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T14:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"ddacf768f72278dea085cc983538b9e3ee188879e16d694443a48e20d40fc554","abstract_canon_sha256":"19e9e6b5d3930b8eab368eb04dcab688ddfe1a834dbcca6b47172490a4b199a0"},"schema_version":"1.0"},"canonical_sha256":"3287151948c8b3831c3d444529ceb0dc340140f2a28675e9be179924d29e9d14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:24.791240Z","signature_b64":"gmb5J12M08/+4GtDXWzKVrb4tnEopLZLyP0CCNVke8Jh/gEdCLcwIFGTqFtVLY+OhMND+rMcmcd8ANQvSAUyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3287151948c8b3831c3d444529ceb0dc340140f2a28675e9be179924d29e9d14","last_reissued_at":"2026-07-05T10:47:24.790704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:24.790704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.10727","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":"2026-07-05T10:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ga/cs8Cram70sbej2tofNqmx4FfTMiPinsq5maFG3E9tsYthboNTITftqZEUbj4erY8/hMjqLRfdQhalxLvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:13:03.305927Z"},"content_sha256":"ed982c3b21c1c42082c325f71ca0ab1e3b6ac970d842073abe6e2315f38d65a8","schema_version":"1.0","event_id":"sha256:ed982c3b21c1c42082c325f71ca0ab1e3b6ac970d842073abe6e2315f38d65a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GKDRKGKIZCZYGHB5IRCSTTVQ3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyu Wang, Lin Ma, Shenghua Gao, Sixun Dong, Weixin Luo, Xiaohua Xuan, Zhengxin Li","submitted_at":"2024-01-19T14:44:37Z","abstract_excerpt":"Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' ability to perceive tool use is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the information in the visual- or auditory-grounded instructions. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10727","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/2401.10727/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":"2026-07-05T10:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6MLtx8g6WloU6vqTNVIYUp4qMNc1faZ4hBWf/+dzdw1W+OAkg+yW3/KJCev4vlnTsrInMhhly7lVK6iLTTCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:13:03.306438Z"},"content_sha256":"1381c2d0a901210c980b70d62cccd564d30bb4b42e6b8367f3e8878a86324102","schema_version":"1.0","event_id":"sha256:1381c2d0a901210c980b70d62cccd564d30bb4b42e6b8367f3e8878a86324102"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/bundle.json","state_url":"https://pith.science/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/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":"2026-08-09T00:13:03Z","links":{"resolver":"https://pith.science/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q","bundle":"https://pith.science/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/bundle.json","state":"https://pith.science/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKDRKGKIZCZYGHB5IRCSTTVQ3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GKDRKGKIZCZYGHB5IRCSTTVQ3Q","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":"19e9e6b5d3930b8eab368eb04dcab688ddfe1a834dbcca6b47172490a4b199a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T14:44:37Z","title_canon_sha256":"ddacf768f72278dea085cc983538b9e3ee188879e16d694443a48e20d40fc554"},"schema_version":"1.0","source":{"id":"2401.10727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10727","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10727v3","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10727","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"GKDRKGKIZCZY","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_16","alias_value":"GKDRKGKIZCZYGHB5","created_at":"2026-07-05T10:47:24Z"},{"alias_kind":"pith_short_8","alias_value":"GKDRKGKI","created_at":"2026-07-05T10:47:24Z"}],"graph_snapshots":[{"event_id":"sha256:1381c2d0a901210c980b70d62cccd564d30bb4b42e6b8367f3e8878a86324102","target":"graph","created_at":"2026-07-05T10:47:24Z","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/2401.10727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' ability to perceive tool use is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the information in the visual- or auditory-grounded instructions. The","authors_text":"Chenyu Wang, Lin Ma, Shenghua Gao, Sixun Dong, Weixin Luo, Xiaohua Xuan, Zhengxin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T14:44:37Z","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10727","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:ed982c3b21c1c42082c325f71ca0ab1e3b6ac970d842073abe6e2315f38d65a8","target":"record","created_at":"2026-07-05T10:47:24Z","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":"19e9e6b5d3930b8eab368eb04dcab688ddfe1a834dbcca6b47172490a4b199a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T14:44:37Z","title_canon_sha256":"ddacf768f72278dea085cc983538b9e3ee188879e16d694443a48e20d40fc554"},"schema_version":"1.0","source":{"id":"2401.10727","kind":"arxiv","version":3}},"canonical_sha256":"3287151948c8b3831c3d444529ceb0dc340140f2a28675e9be179924d29e9d14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3287151948c8b3831c3d444529ceb0dc340140f2a28675e9be179924d29e9d14","first_computed_at":"2026-07-05T10:47:24.790704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:24.790704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gmb5J12M08/+4GtDXWzKVrb4tnEopLZLyP0CCNVke8Jh/gEdCLcwIFGTqFtVLY+OhMND+rMcmcd8ANQvSAUyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:24.791240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed982c3b21c1c42082c325f71ca0ab1e3b6ac970d842073abe6e2315f38d65a8","sha256:1381c2d0a901210c980b70d62cccd564d30bb4b42e6b8367f3e8878a86324102"],"state_sha256":"fd82afa40dbecc0b145398e8efe2c6dd1c0f9585597e4a48ec53ea7e0b5b24ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jPZUub7iDQGonjRsscIAJ/kvxbQKjFhg+2r5rHECNfNdjLgJaT5V+la2vz3vGp5d3w7AVqnWVf9Xwn8tkA1+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:13:03.311536Z","bundle_sha256":"8cbfa65cf6c2f8c9c34ecbf114c90fe97cb39255a2595aba94e17b05fee86aa5"}}