{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GP7WC6COQEEIIW3X6QTTHGY3KI","short_pith_number":"pith:GP7WC6CO","canonical_record":{"source":{"id":"2401.00127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T03:19:54Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"8c22e1c7cd37ae60b281134e28eb5dbe6e8f8fa529a7dfa619c52cf72d0bc9fd","abstract_canon_sha256":"eaabf47faea78791f97e348f1ffddd22646fa3dd82b689684184bc116f60edb3"},"schema_version":"1.0"},"canonical_sha256":"33ff61784e8108845b77f427339b1b5216fce46258840098c088d4618983069e","source":{"kind":"arxiv","id":"2401.00127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00127","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00127v1","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00127","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"GP7WC6COQEEI","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"GP7WC6COQEEIIW3X","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"GP7WC6CO","created_at":"2026-07-05T07:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GP7WC6COQEEIIW3X6QTTHGY3KI","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T03:19:54Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"8c22e1c7cd37ae60b281134e28eb5dbe6e8f8fa529a7dfa619c52cf72d0bc9fd","abstract_canon_sha256":"eaabf47faea78791f97e348f1ffddd22646fa3dd82b689684184bc116f60edb3"},"schema_version":"1.0"},"canonical_sha256":"33ff61784e8108845b77f427339b1b5216fce46258840098c088d4618983069e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:01.119465Z","signature_b64":"ldN+8YTJ+lU2EuGKIQPHFHOKUc4PXj3mvU7hAqLPW3alc/Io99YuxAtlIoawyhAdIMxRaaNwHgVh96abBrZpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ff61784e8108845b77f427339b1b5216fce46258840098c088d4618983069e","last_reissued_at":"2026-07-05T07:29:01.119003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:01.119003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00127","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":"2026-07-05T07:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfKvSZTyEBMHKXJzWJZRjuezwAsYsQdm/gMfwt5Mq4O8jSYBW9oOB8zDPuo1g2NGLKDtQ0T0LvWiGUukINFcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:36.223591Z"},"content_sha256":"537c379341fa271e03f5216a9efa8db3ee68d80328594bd71b3ed28fa1a61232","schema_version":"1.0","event_id":"sha256:537c379341fa271e03f5216a9efa8db3ee68d80328594bd71b3ed28fa1a61232"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GP7WC6COQEEIIW3X6QTTHGY3KI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CV","authors_text":"Ashhadul Islam, Md. Rafiul Biswas, Samir Brahim Belhaouari, Wajdi Zaghouani, Zubair Shah","submitted_at":"2023-12-30T03:19:54Z","abstract_excerpt":"$ $The synergy of language and vision models has given rise to Large Language and Vision Assistant models (LLVAs), designed to engage users in rich conversational experiences intertwined with image-based queries. These comprehensive multimodal models seamlessly integrate vision encoders with Large Language Models (LLMs), expanding their applications in general-purpose language and visual comprehension. The advent of Large Multimodal Models (LMMs) heralds a new era in Artificial Intelligence (AI) assistance, extending the horizons of AI utilization. This paper takes a unique perspective on LMMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00127","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/2401.00127/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":"2026-07-05T07:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruycHH1sydXPOfdC/wV7XQ4H6Ejv2mZDsrXXW5BoySJzWOR8Uv2+n2p1DhI41Bm0JDFk1NmwTsFUBTtbt+NtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:36.224097Z"},"content_sha256":"28355a7dbea412a1f03e1f7148ffd471ea48b703e5dc84ccff1a6217bf6f31e5","schema_version":"1.0","event_id":"sha256:28355a7dbea412a1f03e1f7148ffd471ea48b703e5dc84ccff1a6217bf6f31e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/bundle.json","state_url":"https://pith.science/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/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":"2026-08-08T12:55:36Z","links":{"resolver":"https://pith.science/pith/GP7WC6COQEEIIW3X6QTTHGY3KI","bundle":"https://pith.science/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/bundle.json","state":"https://pith.science/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GP7WC6COQEEIIW3X6QTTHGY3KI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GP7WC6COQEEIIW3X6QTTHGY3KI","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":"eaabf47faea78791f97e348f1ffddd22646fa3dd82b689684184bc116f60edb3","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T03:19:54Z","title_canon_sha256":"8c22e1c7cd37ae60b281134e28eb5dbe6e8f8fa529a7dfa619c52cf72d0bc9fd"},"schema_version":"1.0","source":{"id":"2401.00127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00127","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00127v1","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00127","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"GP7WC6COQEEI","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"GP7WC6COQEEIIW3X","created_at":"2026-07-05T07:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"GP7WC6CO","created_at":"2026-07-05T07:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:28355a7dbea412a1f03e1f7148ffd471ea48b703e5dc84ccff1a6217bf6f31e5","target":"graph","created_at":"2026-07-05T07:29:01Z","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/2401.00127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"$ $The synergy of language and vision models has given rise to Large Language and Vision Assistant models (LLVAs), designed to engage users in rich conversational experiences intertwined with image-based queries. These comprehensive multimodal models seamlessly integrate vision encoders with Large Language Models (LLMs), expanding their applications in general-purpose language and visual comprehension. The advent of Large Multimodal Models (LMMs) heralds a new era in Artificial Intelligence (AI) assistance, extending the horizons of AI utilization. This paper takes a unique perspective on LMMs","authors_text":"Ashhadul Islam, Md. Rafiul Biswas, Samir Brahim Belhaouari, Wajdi Zaghouani, Zubair Shah","cross_cats":["cs.SI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T03:19:54Z","title":"Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00127","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":"sha256:537c379341fa271e03f5216a9efa8db3ee68d80328594bd71b3ed28fa1a61232","target":"record","created_at":"2026-07-05T07:29:01Z","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":"eaabf47faea78791f97e348f1ffddd22646fa3dd82b689684184bc116f60edb3","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T03:19:54Z","title_canon_sha256":"8c22e1c7cd37ae60b281134e28eb5dbe6e8f8fa529a7dfa619c52cf72d0bc9fd"},"schema_version":"1.0","source":{"id":"2401.00127","kind":"arxiv","version":1}},"canonical_sha256":"33ff61784e8108845b77f427339b1b5216fce46258840098c088d4618983069e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33ff61784e8108845b77f427339b1b5216fce46258840098c088d4618983069e","first_computed_at":"2026-07-05T07:29:01.119003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:01.119003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldN+8YTJ+lU2EuGKIQPHFHOKUc4PXj3mvU7hAqLPW3alc/Io99YuxAtlIoawyhAdIMxRaaNwHgVh96abBrZpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:01.119465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:537c379341fa271e03f5216a9efa8db3ee68d80328594bd71b3ed28fa1a61232","sha256:28355a7dbea412a1f03e1f7148ffd471ea48b703e5dc84ccff1a6217bf6f31e5"],"state_sha256":"86f879b73bfaacf2419fc6acb699cbd681520ff9c6361191ab235174769f95d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFD43/04G5OVgkVV7bNHiHE+zIg6dOTN93NC7kQtEozH14QxoLUO0PV+GpIIzJHjjToguZ5tM2gwWYcnL+UjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:55:36.227567Z","bundle_sha256":"947e524f46bca88f2ff29433cc1c3daeb0aef4ea7e02d6ec21c35157a3689fee"}}