{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GMUU6W2VMHIAXKRLXMWAXTA4YU","short_pith_number":"pith:GMUU6W2V","canonical_record":{"source":{"id":"2405.15668","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T16:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"b16b3d601a52197ef9226f750bec377774c0f7ba89a8d941e228e9e426bc204f","abstract_canon_sha256":"e96b33b7ce7eb6b0a68c8f8eb2fdb10fbce7551d992211cde1af90d879abd08e"},"schema_version":"1.0"},"canonical_sha256":"33294f5b5561d00baa2bbb2c0bcc1cc5312bc58d10e9ca1ad7d69170e22638a3","source":{"kind":"arxiv","id":"2405.15668","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15668","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15668v5","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15668","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"GMUU6W2VMHIA","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"GMUU6W2VMHIAXKRL","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"GMUU6W2V","created_at":"2026-07-05T11:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GMUU6W2VMHIAXKRLXMWAXTA4YU","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15668","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T16:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"b16b3d601a52197ef9226f750bec377774c0f7ba89a8d941e228e9e426bc204f","abstract_canon_sha256":"e96b33b7ce7eb6b0a68c8f8eb2fdb10fbce7551d992211cde1af90d879abd08e"},"schema_version":"1.0"},"canonical_sha256":"33294f5b5561d00baa2bbb2c0bcc1cc5312bc58d10e9ca1ad7d69170e22638a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:18.672397Z","signature_b64":"TxjRSR+TIyUw4NB85AXDMHDnCgcyrw1u7OdCs/MpHJcnJ/N7IB9j8L3eXOcKzl6xe7hcv10k8f/vLbHMb5AcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33294f5b5561d00baa2bbb2c0bcc1cc5312bc58d10e9ca1ad7d69170e22638a3","last_reissued_at":"2026-07-05T11:27:18.671922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:18.671922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15668","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X7zlEE2CibAKuKLdIHKzgvnMEtFQEswdZgDwPTZ1gSfyCivPiIjXqLMBC3lj05Etbs7hti9pBcvw4b6XqnZvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:28:41.536062Z"},"content_sha256":"68da5e8e61cf7a4b1775b95a3615975e707ad0a90932933037cc161d6e32fa75","schema_version":"1.0","event_id":"sha256:68da5e8e61cf7a4b1775b95a3615975e707ad0a90932933037cc161d6e32fa75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GMUU6W2VMHIAXKRLXMWAXTA4YU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Abdelhamed, Alec Go, Mahmoud Afifi","submitted_at":"2024-05-24T16:05:15Z","abstract_excerpt":"Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs. Using multimodal LLMs, we generate comprehensive textual representations from input images. These textual representations are then utilized to generate fixed-dimensional features in a cross-modal embedding space. Subsequently, these features are fused together to perform zero-shot classification using a linear classifier. Our method does not require prompt engin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15668","kind":"arxiv","version":5},"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/2405.15668/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":"2026-07-05T11:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzeyM/dc4R7HXm3k0qAfej4dXExMEChfgbyXCxUM34PoihKpCzNz3iI1ETvGm7CCMQFLz9riNyTL33pav2goAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:28:41.536559Z"},"content_sha256":"e65ceaba2493840c16fe631992cae1ffa9d196238db8b660272d101859561e5c","schema_version":"1.0","event_id":"sha256:e65ceaba2493840c16fe631992cae1ffa9d196238db8b660272d101859561e5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/bundle.json","state_url":"https://pith.science/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/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":"2026-08-06T12:28:41Z","links":{"resolver":"https://pith.science/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU","bundle":"https://pith.science/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/bundle.json","state":"https://pith.science/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMUU6W2VMHIAXKRLXMWAXTA4YU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GMUU6W2VMHIAXKRLXMWAXTA4YU","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":"e96b33b7ce7eb6b0a68c8f8eb2fdb10fbce7551d992211cde1af90d879abd08e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T16:05:15Z","title_canon_sha256":"b16b3d601a52197ef9226f750bec377774c0f7ba89a8d941e228e9e426bc204f"},"schema_version":"1.0","source":{"id":"2405.15668","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15668","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15668v5","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15668","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"GMUU6W2VMHIA","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"GMUU6W2VMHIAXKRL","created_at":"2026-07-05T11:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"GMUU6W2V","created_at":"2026-07-05T11:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:e65ceaba2493840c16fe631992cae1ffa9d196238db8b660272d101859561e5c","target":"graph","created_at":"2026-07-05T11:27:18Z","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/2405.15668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs. Using multimodal LLMs, we generate comprehensive textual representations from input images. These textual representations are then utilized to generate fixed-dimensional features in a cross-modal embedding space. Subsequently, these features are fused together to perform zero-shot classification using a linear classifier. Our method does not require prompt engin","authors_text":"Abdelrahman Abdelhamed, Alec Go, Mahmoud Afifi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T16:05:15Z","title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15668","kind":"arxiv","version":5},"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":"sha256:68da5e8e61cf7a4b1775b95a3615975e707ad0a90932933037cc161d6e32fa75","target":"record","created_at":"2026-07-05T11:27:18Z","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":"e96b33b7ce7eb6b0a68c8f8eb2fdb10fbce7551d992211cde1af90d879abd08e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T16:05:15Z","title_canon_sha256":"b16b3d601a52197ef9226f750bec377774c0f7ba89a8d941e228e9e426bc204f"},"schema_version":"1.0","source":{"id":"2405.15668","kind":"arxiv","version":5}},"canonical_sha256":"33294f5b5561d00baa2bbb2c0bcc1cc5312bc58d10e9ca1ad7d69170e22638a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33294f5b5561d00baa2bbb2c0bcc1cc5312bc58d10e9ca1ad7d69170e22638a3","first_computed_at":"2026-07-05T11:27:18.671922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:18.671922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TxjRSR+TIyUw4NB85AXDMHDnCgcyrw1u7OdCs/MpHJcnJ/N7IB9j8L3eXOcKzl6xe7hcv10k8f/vLbHMb5AcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:18.672397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15668","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68da5e8e61cf7a4b1775b95a3615975e707ad0a90932933037cc161d6e32fa75","sha256:e65ceaba2493840c16fe631992cae1ffa9d196238db8b660272d101859561e5c"],"state_sha256":"9ba6a4e714e7cd5fcfa629264a4ee5ff9e9129a682ca2616642facbab1d6787c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KGNncD7DW/QbAiCm2hkxj0h4jGGhsL+hbUPWyKJmZEmY1KcRsOaevjOu/OwWfVs5YGJfUgJk2El5BJKgzDlXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:28:41.540788Z","bundle_sha256":"6f96f99714a64dcaaebafb17bf371d7499abe4bf52033ed99340b1074512b8b8"}}