{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:24NU3PBSHPSXYQ2CWFQ6IZVTTC","short_pith_number":"pith:24NU3PBS","canonical_record":{"source":{"id":"2312.15011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T18:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"f5bfd03faee633229aa9bdb08669690e91c407a6ab0423ee2a65ea43c598101e","abstract_canon_sha256":"2e6446bcfb6799c6aca5e4de15b74e84dd6e5b00e1df83e2f0404d13e2fb9352"},"schema_version":"1.0"},"canonical_sha256":"d71b4dbc323be57c4342b161e466b398b0fefd9f222b0fb5d938d9bf7dca6b38","source":{"kind":"arxiv","id":"2312.15011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15011","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15011v1","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15011","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"24NU3PBSHPSX","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"24NU3PBSHPSXYQ2C","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"24NU3PBS","created_at":"2026-07-05T07:27:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:24NU3PBSHPSXYQ2CWFQ6IZVTTC","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T18:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"f5bfd03faee633229aa9bdb08669690e91c407a6ab0423ee2a65ea43c598101e","abstract_canon_sha256":"2e6446bcfb6799c6aca5e4de15b74e84dd6e5b00e1df83e2f0404d13e2fb9352"},"schema_version":"1.0"},"canonical_sha256":"d71b4dbc323be57c4342b161e466b398b0fefd9f222b0fb5d938d9bf7dca6b38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:29.713930Z","signature_b64":"CikxuMxseQzOQlGV1QpamVoMRUzBN93unbp88U0z4F/LrKfpZILtfS0W1choBSIPSLlsz1ZdAuhsfFdOHTfmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71b4dbc323be57c4342b161e466b398b0fefd9f222b0fb5d938d9bf7dca6b38","last_reissued_at":"2026-07-05T07:27:29.713479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:29.713479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15011","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":"2026-07-05T07:27:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFY6hCsDjmzWygtc2JKoLwFSBE7aQfQwWxFOs1gHhxIsUi4x5Hd7oTOU5myLmouBigX5oRv1Cbxx/ZLWc+BXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:12:17.459223Z"},"content_sha256":"d5698f4caaa9a1378e950ee95ef924ec58ed4db95c31242f734c51eb9d7e39b9","schema_version":"1.0","event_id":"sha256:d5698f4caaa9a1378e950ee95ef924ec58ed4db95c31242f734c51eb9d7e39b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:24NU3PBSHPSXYQ2CWFQ6IZVTTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Hengshuang Zhao, Jiaqi Wang, Mengchen Zhang, Tong Wu, Ye Fang, Zeyi Sun, Zhangyang Qi, Ziwei Liu","submitted_at":"2023-12-22T18:59:58Z","abstract_excerpt":"The rapidly evolving sector of Multi-modal Large Language Models (MLLMs) is at the forefront of integrating linguistic and visual processing in artificial intelligence. This paper presents an in-depth comparative study of two pioneering models: Google's Gemini and OpenAI's GPT-4V(ision). Our study involves a multi-faceted evaluation of both models across key dimensions such as Vision-Language Capability, Interaction with Humans, Temporal Understanding, and assessments in both Intelligence and Emotional Quotients. The core of our analysis delves into the distinct visual comprehension abilities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15011","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/2312.15011/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":"2026-07-05T07:27:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSjyCT7ZnPkGnSa1EvZPznkX9XAZ/seER78UWle20msEjiHZm8O5JJ4jigH2KsH6LNwr5wWojRrbclr0hPFSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:12:17.459735Z"},"content_sha256":"7ef2284403fac7309e1ef0612ca92107569a8f5d3abe4023b86e072562920476","schema_version":"1.0","event_id":"sha256:7ef2284403fac7309e1ef0612ca92107569a8f5d3abe4023b86e072562920476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/bundle.json","state_url":"https://pith.science/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/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":"2026-08-03T19:12:17Z","links":{"resolver":"https://pith.science/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC","bundle":"https://pith.science/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/bundle.json","state":"https://pith.science/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24NU3PBSHPSXYQ2CWFQ6IZVTTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:24NU3PBSHPSXYQ2CWFQ6IZVTTC","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":"2e6446bcfb6799c6aca5e4de15b74e84dd6e5b00e1df83e2f0404d13e2fb9352","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T18:59:58Z","title_canon_sha256":"f5bfd03faee633229aa9bdb08669690e91c407a6ab0423ee2a65ea43c598101e"},"schema_version":"1.0","source":{"id":"2312.15011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15011","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15011v1","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15011","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"24NU3PBSHPSX","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"24NU3PBSHPSXYQ2C","created_at":"2026-07-05T07:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"24NU3PBS","created_at":"2026-07-05T07:27:29Z"}],"graph_snapshots":[{"event_id":"sha256:7ef2284403fac7309e1ef0612ca92107569a8f5d3abe4023b86e072562920476","target":"graph","created_at":"2026-07-05T07:27:29Z","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/2312.15011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapidly evolving sector of Multi-modal Large Language Models (MLLMs) is at the forefront of integrating linguistic and visual processing in artificial intelligence. This paper presents an in-depth comparative study of two pioneering models: Google's Gemini and OpenAI's GPT-4V(ision). Our study involves a multi-faceted evaluation of both models across key dimensions such as Vision-Language Capability, Interaction with Humans, Temporal Understanding, and assessments in both Intelligence and Emotional Quotients. The core of our analysis delves into the distinct visual comprehension abilities ","authors_text":"Dahua Lin, Hengshuang Zhao, Jiaqi Wang, Mengchen Zhang, Tong Wu, Ye Fang, Zeyi Sun, Zhangyang Qi, Ziwei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T18:59:58Z","title":"Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15011","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:d5698f4caaa9a1378e950ee95ef924ec58ed4db95c31242f734c51eb9d7e39b9","target":"record","created_at":"2026-07-05T07:27:29Z","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":"2e6446bcfb6799c6aca5e4de15b74e84dd6e5b00e1df83e2f0404d13e2fb9352","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T18:59:58Z","title_canon_sha256":"f5bfd03faee633229aa9bdb08669690e91c407a6ab0423ee2a65ea43c598101e"},"schema_version":"1.0","source":{"id":"2312.15011","kind":"arxiv","version":1}},"canonical_sha256":"d71b4dbc323be57c4342b161e466b398b0fefd9f222b0fb5d938d9bf7dca6b38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d71b4dbc323be57c4342b161e466b398b0fefd9f222b0fb5d938d9bf7dca6b38","first_computed_at":"2026-07-05T07:27:29.713479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:29.713479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CikxuMxseQzOQlGV1QpamVoMRUzBN93unbp88U0z4F/LrKfpZILtfS0W1choBSIPSLlsz1ZdAuhsfFdOHTfmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:29.713930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5698f4caaa9a1378e950ee95ef924ec58ed4db95c31242f734c51eb9d7e39b9","sha256:7ef2284403fac7309e1ef0612ca92107569a8f5d3abe4023b86e072562920476"],"state_sha256":"0ef8e3c060253a006c5b0df6b646b485110f9dc0b0dfd7172b73d8b1590cb1a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wnrkFqCXMFgAoc+8zYRXj0TU4EPafs1mC7PWrCR0kuLCs07+/YmcHzbC0an7WF8RwSaCXwRGfQb+fYP6j/SCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:12:17.465045Z","bundle_sha256":"036a9967e434ffc589a338da502a33ee938d0ff6df6ffae1c0ceabe17801dba9"}}