{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ISWRIHHVTSDI6Z5FOMJT2AXKAA","short_pith_number":"pith:ISWRIHHV","canonical_record":{"source":{"id":"2403.09027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T01:39:40Z","cross_cats_sorted":[],"title_canon_sha256":"7c467bfccc67151a2637e24e8eab799c1686bf47659730f1b1c2418408155825","abstract_canon_sha256":"345ed1b3db80ee1c305a23f1a96fc866d6f788106289d72d68cf2be80f9d0fb6"},"schema_version":"1.0"},"canonical_sha256":"44ad141cf59c868f67a573133d02ea0010b4acdb643dcfe012c78525c93d2f2f","source":{"kind":"arxiv","id":"2403.09027","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09027","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09027v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09027","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"ISWRIHHVTSDI","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"ISWRIHHVTSDI6Z5F","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"ISWRIHHV","created_at":"2026-07-05T07:55:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ISWRIHHVTSDI6Z5FOMJT2AXKAA","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T01:39:40Z","cross_cats_sorted":[],"title_canon_sha256":"7c467bfccc67151a2637e24e8eab799c1686bf47659730f1b1c2418408155825","abstract_canon_sha256":"345ed1b3db80ee1c305a23f1a96fc866d6f788106289d72d68cf2be80f9d0fb6"},"schema_version":"1.0"},"canonical_sha256":"44ad141cf59c868f67a573133d02ea0010b4acdb643dcfe012c78525c93d2f2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:50.775442Z","signature_b64":"9bBUl6kU+nkBwsiRaicQeUSNb54lb6N5UW4lfVKJrwWoqMGfd++k7r7l99yBijPrAq+DPp2wV1atlRhw2MoUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ad141cf59c868f67a573133d02ea0010b4acdb643dcfe012c78525c93d2f2f","last_reissued_at":"2026-07-05T07:55:50.774986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:50.774986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09027","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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LlVrCjrxgx8u742b/TqNS3XeK2xjE6ao923zYHPoukB2+P9V9VPZBiT10Dv8Dzl0wc1Icls462rSLyGtaP3gDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:50:43.784528Z"},"content_sha256":"abd9775b5748f9cd4d99a6f56845a8765cdcd454a712516bf54042ca0e929864","schema_version":"1.0","event_id":"sha256:abd9775b5748f9cd4d99a6f56845a8765cdcd454a712516bf54042ca0e929864"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ISWRIHHVTSDI6Z5FOMJT2AXKAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Yang, Chris Kelly, Cindy Yang, Deshun Yang, Jiayin Hu, Luhui Hu, Yuexian Zou, Yu Tian, Zaoshan Huang, Zihao Li","submitted_at":"2024-03-14T01:39:40Z","abstract_excerpt":"With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09027","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/2403.09027/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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvnH0ffoLHSbrLAHSKmCPqvonavBoEbGNGqz8mx+VIcf3dq0LvYKOANP0Dco28O3ijAPu3JcTxdWW30Bk0ZRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:50:43.784907Z"},"content_sha256":"f7d92839ec4a7f66d129693f183c1e6f95d46558e61e5f062ebf215508f03c67","schema_version":"1.0","event_id":"sha256:f7d92839ec4a7f66d129693f183c1e6f95d46558e61e5f062ebf215508f03c67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/bundle.json","state_url":"https://pith.science/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/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":"2026-07-05T12:50:43Z","links":{"resolver":"https://pith.science/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA","bundle":"https://pith.science/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/bundle.json","state":"https://pith.science/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISWRIHHVTSDI6Z5FOMJT2AXKAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ISWRIHHVTSDI6Z5FOMJT2AXKAA","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":"345ed1b3db80ee1c305a23f1a96fc866d6f788106289d72d68cf2be80f9d0fb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T01:39:40Z","title_canon_sha256":"7c467bfccc67151a2637e24e8eab799c1686bf47659730f1b1c2418408155825"},"schema_version":"1.0","source":{"id":"2403.09027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09027","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09027v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09027","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"ISWRIHHVTSDI","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"ISWRIHHVTSDI6Z5F","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"ISWRIHHV","created_at":"2026-07-05T07:55:50Z"}],"graph_snapshots":[{"event_id":"sha256:f7d92839ec4a7f66d129693f183c1e6f95d46558e61e5f062ebf215508f03c67","target":"graph","created_at":"2026-07-05T07:55:50Z","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/2403.09027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) a","authors_text":"Bang Yang, Chris Kelly, Cindy Yang, Deshun Yang, Jiayin Hu, Luhui Hu, Yuexian Zou, Yu Tian, Zaoshan Huang, Zihao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T01:39:40Z","title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09027","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:abd9775b5748f9cd4d99a6f56845a8765cdcd454a712516bf54042ca0e929864","target":"record","created_at":"2026-07-05T07:55:50Z","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":"345ed1b3db80ee1c305a23f1a96fc866d6f788106289d72d68cf2be80f9d0fb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T01:39:40Z","title_canon_sha256":"7c467bfccc67151a2637e24e8eab799c1686bf47659730f1b1c2418408155825"},"schema_version":"1.0","source":{"id":"2403.09027","kind":"arxiv","version":1}},"canonical_sha256":"44ad141cf59c868f67a573133d02ea0010b4acdb643dcfe012c78525c93d2f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44ad141cf59c868f67a573133d02ea0010b4acdb643dcfe012c78525c93d2f2f","first_computed_at":"2026-07-05T07:55:50.774986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:50.774986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9bBUl6kU+nkBwsiRaicQeUSNb54lb6N5UW4lfVKJrwWoqMGfd++k7r7l99yBijPrAq+DPp2wV1atlRhw2MoUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:50.775442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abd9775b5748f9cd4d99a6f56845a8765cdcd454a712516bf54042ca0e929864","sha256:f7d92839ec4a7f66d129693f183c1e6f95d46558e61e5f062ebf215508f03c67"],"state_sha256":"73d98bf5f8f2e8fd076b09991871b5d77bf2f8f63cb2a849cdefba3b0b45b7be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FDojP+5QYUPEUInwylcawmd2wlW1I0qUW9fuY/y2WSNpWWAewohE6cs+bj67x/6LHaEfbXeAiTFJB/0TNInBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:50:43.787390Z","bundle_sha256":"2f9c04f0711f1b20ce291b81aa2d1c1994d552ecb597fa6170c9baa2617d2d31"}}